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 2022/05/27 13:14:05 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@aaee8aa441ba9be3934dbfa358767d54f2b2e159)
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 6f5d90ee6 deploying docs (apache/tvm@aaee8aa441ba9be3934dbfa358767d54f2b2e159)
6f5d90ee6 is described below
commit 6f5d90ee6341ca3da9b81829ecdcbdba8bb55d2b
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri May 27 13:13:58 2022 +0000
deploying docs (apache/tvm@aaee8aa441ba9be3934dbfa358767d54f2b2e159)
---
.../how_to/compile_models/from_darknet.rst.txt | 5 -
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 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 | 18 +-
.../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 | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 2010 +++++++++++---------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 465 +----
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 11 +-
docs/_sources/tutorial/autotvm_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 | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 1 -
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 78 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 8 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 42 +-
docs/how_to/deploy_models/deploy_prequantized.html | 11 +-
.../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 | 18 +-
.../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 | 2010 +++++++++++---------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 465 +----
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/doxygen/functions_d.html | 2 +-
docs/reference/api/doxygen/functions_k.html | 2 +-
docs/reference/api/doxygen/functions_o.html | 2 +-
docs/reference/api/doxygen/functions_vars_d.html | 2 +-
docs/reference/api/doxygen/functions_vars_k.html | 2 +-
docs/reference/api/doxygen/functions_vars_o.html | 2 +-
.../api/doxygen/relay_2attrs_2nn_8h_source.html | 8 +-
docs/reference/api/doxygen/search/all_10.js | 2 +-
docs/reference/api/doxygen/search/all_5.js | 2 +-
docs/reference/api/doxygen/search/all_c.js | 2 +-
docs/reference/api/doxygen/search/variables_4.js | 2 +-
docs/reference/api/doxygen/search/variables_a.js | 2 +-
docs/reference/api/doxygen/search/variables_e.js | 2 +-
...m_1_1relay_1_1Conv3DTransposeAttrs-members.html | 6 +-
...structtvm_1_1relay_1_1Conv3DTransposeAttrs.html | 32 +-
...1relay_1_1Conv3DTransposeAttrs__coll__graph.svg | 457 +++--
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 | 6 +-
.../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 | 6 +-
docs/tutorial/autotvm_relay_x86.html | 264 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
133 files changed, 3446 insertions(+), 3702 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 68da28e30..2bdb67d0e 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -287,11 +287,6 @@ The process is no different from other examples.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.451 seconds)
-
-
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 57544b377..c0783e187 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa91db0de-31a0-4a62-a78b-f9d973d9753a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf950dfa4-db27-4e8f-a5a9-740ed2e4ca4d 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 e8ee3fa87..ff039024a 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ 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<07:23, 98.1kB/s]
0%| | 48.0k/41.5M [00:00<04:39, 155kB/s]
0%| | 96.0k/41.5M [00:00<03:19, 218kB/s]
0%| | 184k/41.5M [00:00<02:06, 344kB/s]
1%| | 304k/41.5M [00:00<01:29, 483kB/s]
1%|1 | 576k/41.5M [00:01<00:48, 881kB/s]
2%|2 | 880k/41.5M [00:01<00:35, 1.20MB/s]
4%|4 | 1.73M/41.5M [00:01<00:16, 2.54MB/s]
8%|7 | 3.20M/41.5M [00:01<00:08, 4.63MB/s]
11%|#1 | 4.70M/41.5M [00:01<00:06, 6.07MB/s]
15%|#4 | 6.18M/41.5M [00:01<00:05, 7.05MB/s]
18%|#8 | 7.66M/41.5M [00:02<00:04, 7.72MB/s]
22%|##2 | 9.15M/41.5M [00:02<00:04, 8.18MB/s]
26%|##5 | 10.6M/41.5M [00:02<00:03, 8.51MB/s]
29%|##9 | 12.1M/41.5M [00:02<00:03, 8.75MB/s]
33%|###2 | 13.6M/41.5M [00:02<00:03, 8.90MB/s]
36%|###6 | 15.1M/41.5M [00:02<00:
03, 9.01MB/s]
40%|###9 | 16.6M/41.5M [00:03<00:02, 9.09MB/s]
44%|####3 | 18.1M/41.5M [00:03<00:02, 10.4MB/s]
46%|####6 | 19.2M/41.5M [00:03<00:02, 10.7MB/s]
49%|####8 | 20.3M/41.5M [00:03<00:02, 9.90MB/s]
51%|#####1 | 21.3M/41.5M [00:03<00:02, 8.70MB/s]
54%|#####4 | 22.5M/41.5M [00:03<00:02, 9.63MB/s]
57%|#####7 | 23.7M/41.5M [00:03<00:01, 10.2MB/s]
60%|#####9 | 24.7M/41.5M [00:03<00:01, 9.41MB/s]
62%|######1 | 25.6M/41.5M [00:04<00:02, 8.22MB/s]
65%|######5 | 27.0M/41.5M [00:04<00:01, 9.38MB/s]
68%|######7 | 28.2M/41.5M [00:04<00:01, 9.49MB/s]
70%|####### | 29.1M/41.5M [00:04<00:01, 9.48MB/s]
72%|#######2 | 30.0M/41.5M [00:04<00:01, 8.21MB/s]
76%|#######5 | 31.4M/41.5M [00:04<00:01, 9.74MB/s]
78%|#######8 | 32.6M/41.5M [00:04<00:00, 10.3MB/s]
81%|######## | 33.6M/41.5M [00:04<00:00, 9.41MB/s]
83%|########3 | 34.5M/41.5M [00:05<00:00, 8.20MB/s]
86%|#####
###6 | 35.9M/41.5M [00:05<00:00, 9.60MB/s]
89%|########9 | 37.0M/41.5M [00:05<00:00, 10.1MB/s]
92%|#########1| 38.0M/41.5M [00:05<00:00, 9.29MB/s]
94%|#########3| 39.0M/41.5M [00:05<00:00, 8.11MB/s]
97%|#########7| 40.3M/41.5M [00:05<00:00, 9.59MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 10.2MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 7.56MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:35, 95.5kB/s]
0%| | 40.0k/41.5M [00:00<05:52, 123kB/s]
0%| | 88.0k/41.5M [00:00<03:40, 197kB/s]
0%| | 160k/41.5M [00:00<02:30, 288kB/s]
1%| | 336k/41.5M [00:00<01:17, 559kB/s]
1%|1 | 632k/41.5M [00:01<00:44, 965kB/s]
3%|2 | 1.24M/41.5M [00:01<00:22, 1.88MB/s]
6%|6 | 2.49M/41.5M [00:01<00:11, 3.70MB/s]
10%|9 | 3.96M/41.5M [00:01<00:07, 5.32MB/s]
13%|#3 | 5.43M/41.5M [00:01<00:05, 6.43MB/s]
17%|#6 | 6.90M/41.5M [00:01<00:05, 7.20MB/s]
20%|## | 8.37M/41.5M [00:02<00:04, 7.72MB/s]
24%|##3 | 9.84M/41.5M [00:02<00:04, 8.09MB/s]
27%|##7 | 11.3M/41.5M [00:02<00:03, 8.35MB/s]
31%|### | 12.8M/41.5M [00:02<00:03, 8.51MB/s]
34%|###4 | 14.2M/41.5M [00:02<00:03, 8.65MB/s]
38%|###7 | 15.7M/41.5M [00:02<00
:02, 9.76MB/s]
40%|#### | 16.7M/41.5M [00:02<00:02, 9.82MB/s]
43%|####2 | 17.7M/41.5M [00:03<00:02, 9.10MB/s]
45%|####4 | 18.7M/41.5M [00:03<00:02, 8.13MB/s]
49%|####8 | 20.1M/41.5M [00:03<00:02, 8.40MB/s]
52%|#####2 | 21.6M/41.5M [00:03<00:02, 8.57MB/s]
56%|#####5 | 23.1M/41.5M [00:03<00:02, 8.66MB/s]
59%|#####9 | 24.5M/41.5M [00:03<00:02, 8.74MB/s]
63%|######2 | 26.0M/41.5M [00:04<00:01, 8.79MB/s]
66%|######6 | 27.5M/41.5M [00:04<00:01, 8.83MB/s]
70%|######9 | 28.9M/41.5M [00:04<00:01, 8.86MB/s]
73%|#######3 | 30.4M/41.5M [00:04<00:01, 8.88MB/s]
77%|#######6 | 31.9M/41.5M [00:04<00:01, 8.90MB/s]
80%|######## | 33.3M/41.5M [00:05<00:00, 8.91MB/s]
84%|########3 | 34.8M/41.5M [00:05<00:00, 8.92MB/s]
87%|########7 | 36.3M/41.5M [00:05<00:00, 9.68MB/s]
91%|######### | 37.7M/41.5M [00:05<00:00, 10.5MB/s]
93%|#########3| 38.8M/41.5M [00:05<00:00, 9.62MB/s]
96%|####
#####5| 39.7M/41.5M [00:05<00:00, 8.94MB/s]
98%|#########8| 40.7M/41.5M [00:05<00:00, 8.05MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 7.40MB/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 7165ac2ba..7ac2cd92a 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -210,7 +210,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.840 seconds)
+ **Total running time of the script:** ( 1 minutes 4.955 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 030a02500..985348483 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ 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]
10%|# | 4.68M/44.7M [00:00<00:00, 49.0MB/s]
21%|## | 9.36M/44.7M [00:00<00:00, 47.9MB/s]
72%|#######1 | 32.1M/44.7M [00:00<00:00, 131MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 128MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
14%|#4 | 6.38M/44.7M [00:00<00:00, 66.8MB/s]
29%|##8 | 12.8M/44.7M [00:00<00:00, 64.0MB/s]
86%|########6 | 38.6M/44.7M [00:00<00:00, 156MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 142MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index e0b25d749..d3f4a3345 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -381,7 +381,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.298 seconds)
+ **Total running time of the script:** ( 1 minutes 2.208 seconds)
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
diff --git a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
index e591876d2..04d5e651d 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:48.423** total execution time for **how_to_compile_models** files:
+**05:10.845** total execution time for **how_to_compile_models** files:
-- **01:13.840**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:02.451**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **01:00.298**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:33.552**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:29.681**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.067**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.246**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.123**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.486**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:02.679**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:04.955**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:02.208**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:55.037**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:29.385**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:23.690**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:20.742**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.583**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:18.747**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.087**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.410**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
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 6994a1a04..a58e9aa3c 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
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 14.9208 14.8962 15.2210 14.7275 0.1403
+ 15.7769 15.5907 17.3624 15.4783 0.5460
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 7e3845bee..7eab7aece 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
@@ -108,7 +108,7 @@ 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]
2%|2 | 3.56M/170M [00:00<00:04, 37.0MB/s]
5%|4 | 7.88M/170M [00:00<00:04, 41.4MB/s]
8%|8 | 14.4M/170M [00:00<00:03, 53.1MB/s]
12%|#2 | 21.1M/170M [00:00<00:02, 59.7MB/s]
16%|#5 | 26.8M/170M [00:00<00:02, 57.9MB/s]
19%|#9 | 32.3M/170M [00:00<00:02, 57.5MB/s]
22%|##2 | 37.8M/170M [00:00<00:02, 56.3MB/s]
25%|##5 | 43.2M/170M [00:00<00:02, 56.4MB/s]
29%|##8 | 48.6M/170M [00:01<00:02, 42.6MB/s]
32%|###1 | 53.5M/170M [00:01<00:02, 44.6MB/s]
34%|###4 | 58.1M/170M [00:01<00:02, 45.4MB/s]
38%|###7 | 63.8M/170M [00:01<00:02, 49.2MB/s]
40%|#### | 68.7M/170M [00:01<00:02, 43.9MB/s]
43%|####3 | 73.2M/170M [00:01<00:02, 43.5MB/s]
46%|####5 | 77.5M/170M [00:01<00:02, 43.9MB/s]
49%|####8 | 82.7M/170M [00:01<00:01, 46.8MB/s]
52%|#####1 | 88.0M/170M [00:01<00:01, 49.1MB/
s]
55%|#####4 | 92.8M/170M [00:02<00:01, 42.2MB/s]
57%|#####7 | 97.0M/170M [00:02<00:01, 42.8MB/s]
61%|###### | 103M/170M [00:02<00:01, 48.0MB/s]
64%|######4 | 109M/170M [00:02<00:01, 52.6MB/s]
67%|######7 | 114M/170M [00:02<00:01, 49.5MB/s]
71%|####### | 121M/170M [00:02<00:00, 53.6MB/s]
74%|#######4 | 126M/170M [00:02<00:00, 51.7MB/s]
77%|#######7 | 131M/170M [00:02<00:00, 46.4MB/s]
80%|#######9 | 135M/170M [00:02<00:00, 45.2MB/s]
83%|########3 | 141M/170M [00:03<00:00, 48.9MB/s]
86%|########6 | 147M/170M [00:03<00:00, 51.4MB/s]
89%|########9 | 152M/170M [00:03<00:00, 49.3MB/s]
92%|#########2| 157M/170M [00:03<00:00, 47.7MB/s]
95%|#########4| 161M/170M [00:03<00:00, 46.5MB/s]
98%|#########8| 166M/170M [00:03<00:00, 49.0MB/s]
100%|##########| 170M/170M [00:03<00:00, 48.5MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
12%|#1 | 20.1M/170M [00:00<00:00, 211MB/s]
28%|##7 | 47.3M/170M [00:00<00:00, 254MB/s]
44%|####3 | 74.2M/170M [00:00<00:00, 267MB/s]
60%|#####9 | 101M/170M [00:00<00:00, 273MB/s]
75%|#######5 | 128M/170M [00:00<00:00, 276MB/s]
91%|#########1| 155M/170M [00:00<00:00, 277MB/s]
100%|##########| 170M/170M [00:00<00:00, 271MB/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').
@@ -262,7 +262,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 2.511 seconds)
+ **Total running time of the script:** ( 2 minutes 56.825 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 a37b91bee..ed30ee35b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ 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]
26%|##6 | 3.55M/13.6M [00:00<00:00, 37.2MB/s]
52%|#####2 | 7.11M/13.6M [00:00<00:00, 37.2MB/s]
91%|######### | 12.3M/13.6M [00:00<00:00, 45.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 44.6MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
36%|###5 | 4.88M/13.6M [00:00<00:00, 51.1MB/s]
77%|#######7 | 10.4M/13.6M [00:00<00:00, 55.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 66.7MB/s]
@@ -353,7 +353,7 @@ 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)
- 88.2732 88.1940 88.8165 87.9212 0.2529
+ 90.1554 90.0577 91.3453 89.8888 0.2695
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.686 seconds)
+ **Total running time of the script:** ( 1 minutes 3.558 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 b2797b6fd..25e1358b5 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
@@ -360,7 +360,7 @@ 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)
- 118.3424 118.2984 122.6727 117.5725 0.5796
+ 117.2878 116.9891 122.3920 115.7325 1.0761
@@ -394,7 +394,7 @@ 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 52.755 seconds)
+ **Total running time of the script:** ( 1 minutes 52.041 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 ed5279a34..002d3ef4d 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -223,7 +223,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 51.853 seconds)
+ **Total running time of the script:** ( 1 minutes 8.950 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 2fcb75e79..e2860aa6e 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
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6424/132723 [00:00<00:01, 64233.32KB/s]
12%|#1 | 15284/132723 [00:00<00:01, 78561.36KB/s]
18%|#8 | 24246/132723 [00:00<00:01, 83605.71KB/s]
25%|##4 | 33136/132723 [00:00<00:01, 85692.82KB/s]
32%|###1 | 42050/132723 [00:00<00:01, 86933.23KB/s]
38%|###8 | 50902/132723 [00:00<00:00, 87468.26KB/s]
45%|####5 | 59770/132723 [00:00<00:00, 87861.67KB/s]
52%|#####1 | 68724/132723 [00:00<00:00, 88392.60KB/s]
59%|#####8 | 77674/132723 [00:00<00:00, 88737.60KB/s]
65%|######5 | 86614/132723 [00:01<00:00, 88940.47KB/s]
72%|#######1 | 95514/132723 [00:01<00:00, 88956.44KB/s]
79%|#######8 | 104410/132723 [00:01<00:00, 74968.58KB/s]
85%|########5 | 113305/132723 [00:01<00:00, 78713.04KB/s]
92%|#########1| 121483/132723 [00:01<00:00, 76630.75KB/s]
98%|#########8| 130361/132723 [00:01<00:00, 79978.41KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 82763.09KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6702/132723 [00:00<00:01, 67008.72KB/s]
11%|#1 | 14782/132723 [00:00<00:01, 75117.77KB/s]
17%|#7 | 22903/132723 [00:00<00:01, 77895.41KB/s]
23%|##3 | 31126/132723 [00:00<00:01, 79602.38KB/s]
30%|##9 | 39351/132723 [00:00<00:01, 80555.01KB/s]
36%|###5 | 47561/132723 [00:00<00:01, 81075.50KB/s]
42%|####2 | 55803/132723 [00:00<00:00, 81512.43KB/s]
48%|####8 | 64005/132723 [00:00<00:00, 81670.99KB/s]
54%|#####4 | 72233/132723 [00:00<00:00, 81859.37KB/s]
61%|###### | 80452/132723 [00:01<00:00, 81960.38KB/s]
67%|######6 | 88722/132723 [00:01<00:00, 82185.19KB/s]
73%|#######3 | 96955/132723 [00:01<00:00, 82228.25KB/s]
79%|#######9 | 105214/132723 [00:01<00:00, 82336.90KB/s]
85%|########5 | 113448/132723 [00:01<00:00, 82294.84KB/s]
92%|#########1| 121730/132723 [00:01<00:00, 82452.15KB/s]
98%|########
#7| 129978/132723 [00:01<00:00, 82459.20KB/s]
100%|##########| 132723/132723 [00:01<00:00, 81222.94KB/s]
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 22.892 seconds)
+ **Total running time of the script:** ( 2 minutes 18.835 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 8dd89f010..852f415bb 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
@@ -5,13 +5,13 @@
Computation times
=================
-**11:04.158** total execution time for **how_to_deploy_models** files:
+**10:08.724** total execution time for **how_to_deploy_models** files:
-- **03:02.511**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:22.892**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:52.755**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:51.853**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:04.686**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.016**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.243**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **02:56.825**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:18.835**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:52.041**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:08.950**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:03.558**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.239**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.100**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.176**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 0b3355909..e6ae3cbf7 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
@@ -425,7 +425,7 @@ 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.zip9f51e92b-0a8d-4586-b71c-72ab496afebb from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipae495c75-b9a2-4265-a5ef-b569bcec0291 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -527,7 +527,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- 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 2d762d040..1fa3db005 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:37.579** total execution time for **how_to_extend_tvm** files:
+**00:38.747** total execution time for **how_to_extend_tvm** files:
-- **00:34.159**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.211**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.007**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:35.230**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.261**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.053**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.203**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 2da63e13e..8a3a31a67 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 5738us [5738us] (44.86%; 44.86%)
- FoldScaleAxis: 7052us [2us] (55.14%; 55.14%)
- FoldConstant: 7050us [1467us] (55.12%; 99.97%)
- InferType: 5583us [5583us] (43.65%; 79.20%)
+ InferType: 6056us [6056us] (45.27%; 45.27%)
+ FoldScaleAxis: 7323us [2us] (54.73%; 54.73%)
+ FoldConstant: 7321us [1568us] (54.72%; 99.97%)
+ InferType: 5753us [5753us] (43.00%; 78.59%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 5614us [5614us] (44.43%; 44.43%)
- FoldScaleAxis: 7020us [2us] (55.57%; 55.57%)
- FoldConstant: 7018us [1522us] (55.55%; 99.97%)
- InferType: 5497us [5497us] (43.51%; 78.32%)
+ InferType: 5773us [5773us] (44.82%; 44.82%)
+ FoldScaleAxis: 7108us [2us] (55.18%; 55.18%)
+ FoldConstant: 7107us [1473us] (55.17%; 99.98%)
+ InferType: 5634us [5634us] (43.74%; 79.28%)
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 846a823b6..f146ba02b 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
@@ -299,7 +299,7 @@ latency of convolution.
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
- Convolution: 54.243287 ms
+ Convolution: 54.219296 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 34365c55b..a768d97a0 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
@@ -632,7 +632,7 @@ be able to run on our build server
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
- conv2d with tensor core: 6.618245 ms
+ conv2d with tensor core: 6.507978 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 ee3c52ecb..a4017834c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,10 +118,10 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019255
+ Numpy running time: 0.019207
/workspace/python/tvm/target/target.py:317: 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. "
- Baseline: 3.443456
+ Baseline: 3.334489
@@ -212,7 +212,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.312268
+ Opt1: 0.307748
@@ -311,7 +311,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.344336
+ Opt2: 0.332632
@@ -403,7 +403,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.122771
+ Opt3: 0.118433
@@ -522,7 +522,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110611
+ Opt4: 0.110538
@@ -640,7 +640,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111446
+ Opt5: 0.111227
@@ -761,7 +761,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.146447
+ Opt6: 0.145653
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 96e3611f4..02e129874 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.704** total execution time for **how_to_optimize_operators** files:
+**00:35.014** total execution time for **how_to_optimize_operators** files:
-- **00:32.956**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.477**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.271**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.349**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.445**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.220**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 57aba5368..3f8b72d2b 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
@@ -5,11 +5,11 @@
Computation times
=================
-**04:56.748** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:23.155**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:18.088**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:39.961**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:18.067**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:09.152**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.325**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:07.888** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:34.522**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:18.267**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.276**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:17.457**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.018**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.349**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 f702039f1..5f8afa965 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
@@ -222,469 +222,568 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- 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, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], 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_2 + (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" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 56), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, d [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 168), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (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_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 280), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @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_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 392), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @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_2 + (floordiv(floordiv(threadIdx.x_1, 7), 9)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32 [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 294), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 343), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 441), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 72), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 490), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 80), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 539), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 88), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 588), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 96), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 5096)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 637), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 104), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 686), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 112), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 264), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 5880)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 735), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 120), 192)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 42)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 43)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 49)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 50)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 51)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 52)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 57)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 58)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 59)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 60)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 61)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 62)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 63)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 64)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 65)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 66)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 67)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 68)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 69)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 70)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 71)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 80)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 81)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 82)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 83)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 84)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 85)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 86)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 87)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 88)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 89)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 90)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 91)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 92)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 93)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 94)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 193)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 194)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 196)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 197)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 199)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 202)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 205)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 206)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 208)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 209)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 210)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 211)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 212)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 213)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 214)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 215)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 216)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 217)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 218)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 219)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 220)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 221)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 222)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 223)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 224)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 225)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 226)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 227)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 228)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 229)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 230)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 231)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 232)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 233)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 234)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 235)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 236)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 237)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 238)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 239)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 240)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 241)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 242)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 243)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 244)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 245)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 246)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 247)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 248)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 249)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 250)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 251)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 252)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 253)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 254)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 255)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 256)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 257)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 258)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 259)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 260)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 261)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 262)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 263)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 264)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 265)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 266)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 267)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 268)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 269)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 270)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 271)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 272)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 273)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 274)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 275)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 276)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 277)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 278)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 279)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 280)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 281)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 282)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 283)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 284)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 285)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 286)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 287)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 384)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 385)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 386)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 387)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 388)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 389)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 390)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 391)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 392)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 393)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 394)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 395)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 399)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 400)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 401)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 402)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 403)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 404)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 407)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 408)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 409)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 410)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 411)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 412)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 413)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 414)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 415)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 416)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 417)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 418)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 419)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 420)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 421)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 422)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 423)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 424)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 425)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 426)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 427)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 428)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 429)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 430)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 431)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 432)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 433)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 434)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 435)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 436)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 437)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 438)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 439)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 440)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 441)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 442)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 443)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 444)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 445)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 446)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 447)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 448)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 449)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 450)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 451)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 452)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 453)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 454)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 455)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 456)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 457)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 458)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 459)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 460)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 461)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 462)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 463)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 464)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 465)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 466)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 467)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 468)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 469)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 470)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 471)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 472)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 473)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 474)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 475)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 476)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 477)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 478)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 479)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 576)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 577)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 578)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 579)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 580)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 581)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 582)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 583)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 584)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 585)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 586)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 587)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 588)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 589)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 590)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 591)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 592)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 593)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 594)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 595)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 596)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 597)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 598)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 599)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 600)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 601)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 602)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 603)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 604)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 605)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 606)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 607)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 608)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 610)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 611)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 613)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 614)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 616)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 617)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 619)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 620)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 622)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 623)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 625)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 626)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 627)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 628)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 629)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 630)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 631)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 632)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 633)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 634)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 635)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 636)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 637)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 638)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 639)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 640)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 641)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 642)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 643)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 644)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 645)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 646)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 647)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 648)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 649)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 650)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 651)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 652)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 653)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 654)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 655)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 656)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 657)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 658)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 659)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 660)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 661)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 662)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 663)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 664)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 665)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 666)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 667)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 668)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 669)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 670)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 671)]))
- }
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 336), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -741,7 +840,7 @@ We build the binary and check its correctness and performance.
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 0.332 ms
+ Execution time of this operator: 0.183 ms
@@ -786,32 +885,32 @@ 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=8)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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)
@@ -834,12 +933,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=392)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -861,439 +960,548 @@ 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__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[6144];
+ extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
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 < 8; ++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 * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((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 * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 112) {
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 24) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 40) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 72) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 88) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 96) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 5096)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5096) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 104) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) % 192) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 264) {
- kernel_shared[(((int)threadIdx.x) + 5880)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5880) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 120) % 192) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 88) {
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
@@ -1352,7 +1560,7 @@ 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 23.155 seconds)
+ **Total running time of the script:** ( 2 minutes 34.522 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 a5940a27a..1866be808 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
@@ -616,7 +616,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7129 9.7105 9.7590 9.6691 0.0367
+ 9.7495 9.7583 9.7772 9.7130 0.0270
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 196967ed7..e33b4f570 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
@@ -635,7 +635,7 @@ 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)
- 736.0303 737.0998 741.1594 729.8317 4.6859
+ 761.6180 761.5995 761.8257 761.4287 0.1626
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 18.088 seconds)
+ **Total running time of the script:** ( 1 minutes 18.267 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 75774dd61..4bc145bf5 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
@@ -362,409 +362,76 @@ 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_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_1: int32 = (i.outer.inner*128)
- {
- compute_5: Buffer(compute_4, float32, [512], [])[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
- compute_5[(cse_var_1 + 16)] = 0f32
- compute_5[(cse_var_1 + 17)] = 0f32
- compute_5[(cse_var_1 + 18)] = 0f32
- compute_5[(cse_var_1 + 19)] = 0f32
- compute_5[(cse_var_1 + 20)] = 0f32
- compute_5[(cse_var_1 + 21)] = 0f32
- compute_5[(cse_var_1 + 22)] = 0f32
- compute_5[(cse_var_1 + 23)] = 0f32
- compute_5[(cse_var_1 + 24)] = 0f32
- compute_5[(cse_var_1 + 25)] = 0f32
- compute_5[(cse_var_1 + 26)] = 0f32
- compute_5[(cse_var_1 + 27)] = 0f32
- compute_5[(cse_var_1 + 28)] = 0f32
- compute_5[(cse_var_1 + 29)] = 0f32
- compute_5[(cse_var_1 + 30)] = 0f32
- compute_5[(cse_var_1 + 31)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 48)] = 0f32
- compute_5[(cse_var_1 + 49)] = 0f32
- compute_5[(cse_var_1 + 50)] = 0f32
- compute_5[(cse_var_1 + 51)] = 0f32
- compute_5[(cse_var_1 + 52)] = 0f32
- compute_5[(cse_var_1 + 53)] = 0f32
- compute_5[(cse_var_1 + 54)] = 0f32
- compute_5[(cse_var_1 + 55)] = 0f32
- compute_5[(cse_var_1 + 56)] = 0f32
- compute_5[(cse_var_1 + 57)] = 0f32
- compute_5[(cse_var_1 + 58)] = 0f32
- compute_5[(cse_var_1 + 59)] = 0f32
- compute_5[(cse_var_1 + 60)] = 0f32
- compute_5[(cse_var_1 + 61)] = 0f32
- compute_5[(cse_var_1 + 62)] = 0f32
- compute_5[(cse_var_1 + 63)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 80)] = 0f32
- compute_5[(cse_var_1 + 81)] = 0f32
- compute_5[(cse_var_1 + 82)] = 0f32
- compute_5[(cse_var_1 + 83)] = 0f32
- compute_5[(cse_var_1 + 84)] = 0f32
- compute_5[(cse_var_1 + 85)] = 0f32
- compute_5[(cse_var_1 + 86)] = 0f32
- compute_5[(cse_var_1 + 87)] = 0f32
- compute_5[(cse_var_1 + 88)] = 0f32
- compute_5[(cse_var_1 + 89)] = 0f32
- compute_5[(cse_var_1 + 90)] = 0f32
- compute_5[(cse_var_1 + 91)] = 0f32
- compute_5[(cse_var_1 + 92)] = 0f32
- compute_5[(cse_var_1 + 93)] = 0f32
- compute_5[(cse_var_1 + 94)] = 0f32
- compute_5[(cse_var_1 + 95)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- compute_5[(cse_var_1 + 112)] = 0f32
- compute_5[(cse_var_1 + 113)] = 0f32
- compute_5[(cse_var_1 + 114)] = 0f32
- compute_5[(cse_var_1 + 115)] = 0f32
- compute_5[(cse_var_1 + 116)] = 0f32
- compute_5[(cse_var_1 + 117)] = 0f32
- compute_5[(cse_var_1 + 118)] = 0f32
- compute_5[(cse_var_1 + 119)] = 0f32
- compute_5[(cse_var_1 + 120)] = 0f32
- compute_5[(cse_var_1 + 121)] = 0f32
- compute_5[(cse_var_1 + 122)] = 0f32
- compute_5[(cse_var_1 + 123)] = 0f32
- compute_5[(cse_var_1 + 124)] = 0f32
- compute_5[(cse_var_1 + 125)] = 0f32
- compute_5[(cse_var_1 + 126)] = 0f32
- compute_5[(cse_var_1 + 127)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_131: int32 = (cse_var_1 + 13)
- let cse_var_130: int32 = (cse_var_1 + 14)
- let cse_var_129: int32 = (cse_var_1 + 15)
- let cse_var_128: int32 = (cse_var_1 + 16)
- let cse_var_127: int32 = (cse_var_1 + 17)
- let cse_var_126: int32 = (cse_var_1 + 18)
- let cse_var_125: int32 = (cse_var_1 + 19)
- let cse_var_124: int32 = (cse_var_1 + 2)
- let cse_var_123: int32 = (cse_var_1 + 20)
- let cse_var_122: int32 = (cse_var_1 + 21)
- let cse_var_121: int32 = (cse_var_1 + 22)
- let cse_var_120: int32 = (cse_var_1 + 23)
- let cse_var_119: int32 = (cse_var_1 + 24)
- let cse_var_118: int32 = (cse_var_1 + 25)
- let cse_var_117: int32 = (cse_var_1 + 26)
- let cse_var_116: int32 = (cse_var_1 + 42)
- let cse_var_115: int32 = (cse_var_1 + 28)
- let cse_var_114: int32 = (cse_var_1 + 29)
- let cse_var_113: int32 = (cse_var_1 + 3)
- let cse_var_112: int32 = (cse_var_1 + 30)
- let cse_var_111: int32 = (cse_var_1 + 31)
- let cse_var_110: int32 = (cse_var_1 + 32)
- let cse_var_109: int32 = (cse_var_1 + 33)
- let cse_var_108: int32 = (cse_var_1 + 34)
- let cse_var_107: int32 = (cse_var_1 + 35)
- let cse_var_106: int32 = (cse_var_1 + 36)
- let cse_var_105: int32 = (cse_var_1 + 37)
- let cse_var_104: int32 = (cse_var_1 + 38)
- let cse_var_103: int32 = (cse_var_1 + 39)
- let cse_var_102: int32 = (cse_var_1 + 4)
- let cse_var_101: int32 = (cse_var_1 + 40)
- let cse_var_100: int32 = (cse_var_1 + 27)
- let cse_var_99: int32 = (cse_var_1 + 1)
- let cse_var_98: int32 = (cse_var_1 + 10)
- let cse_var_97: int32 = (cse_var_1 + 100)
- let cse_var_96: int32 = (cse_var_1 + 101)
- let cse_var_95: int32 = (cse_var_1 + 102)
- let cse_var_94: int32 = (cse_var_1 + 103)
- let cse_var_93: int32 = (cse_var_1 + 104)
- let cse_var_92: int32 = (cse_var_1 + 105)
- let cse_var_91: int32 = (cse_var_1 + 106)
- let cse_var_90: int32 = (cse_var_1 + 107)
- let cse_var_89: int32 = (cse_var_1 + 108)
- let cse_var_88: int32 = (cse_var_1 + 109)
- let cse_var_87: int32 = (cse_var_1 + 11)
- let cse_var_86: int32 = (cse_var_1 + 110)
- let cse_var_85: int32 = (cse_var_1 + 111)
- let cse_var_84: int32 = (cse_var_1 + 127)
- let cse_var_83: int32 = (cse_var_1 + 113)
- let cse_var_82: int32 = (cse_var_1 + 114)
- let cse_var_81: int32 = (cse_var_1 + 115)
- let cse_var_80: int32 = (cse_var_1 + 116)
- let cse_var_79: int32 = (cse_var_1 + 117)
- let cse_var_78: int32 = (cse_var_1 + 118)
- let cse_var_77: int32 = (cse_var_1 + 119)
- let cse_var_76: int32 = (cse_var_1 + 12)
- let cse_var_75: int32 = (cse_var_1 + 120)
- let cse_var_74: int32 = (cse_var_1 + 121)
- let cse_var_73: int32 = (cse_var_1 + 122)
- let cse_var_72: int32 = (cse_var_1 + 123)
- let cse_var_71: int32 = (cse_var_1 + 124)
- let cse_var_70: int32 = (cse_var_1 + 125)
- let cse_var_69: int32 = (cse_var_1 + 126)
- let cse_var_68: int32 = (cse_var_1 + 112)
- let cse_var_67: int32 = (cse_var_1 + 72)
- let cse_var_66: int32 = (cse_var_1 + 73)
- let cse_var_65: int32 = (cse_var_1 + 74)
- let cse_var_64: int32 = (cse_var_1 + 75)
- let cse_var_63: int32 = (cse_var_1 + 76)
- let cse_var_62: int32 = (cse_var_1 + 77)
- let cse_var_61: int32 = (cse_var_1 + 78)
- let cse_var_60: int32 = (cse_var_1 + 79)
- let cse_var_59: int32 = (cse_var_1 + 8)
- let cse_var_58: int32 = (cse_var_1 + 80)
- let cse_var_57: int32 = (cse_var_1 + 81)
- let cse_var_56: int32 = (cse_var_1 + 82)
- let cse_var_55: int32 = (cse_var_1 + 83)
- let cse_var_54: int32 = (cse_var_1 + 84)
- let cse_var_53: int32 = (cse_var_1 + 85)
- let cse_var_52: int32 = (cse_var_1 + 41)
- let cse_var_51: int32 = (cse_var_1 + 87)
- let cse_var_50: int32 = (cse_var_1 + 88)
- let cse_var_49: int32 = (cse_var_1 + 89)
- let cse_var_48: int32 = (cse_var_1 + 9)
- let cse_var_47: int32 = (cse_var_1 + 90)
- let cse_var_46: int32 = (cse_var_1 + 91)
- let cse_var_45: int32 = (cse_var_1 + 92)
- let cse_var_44: int32 = (cse_var_1 + 93)
- let cse_var_43: int32 = (cse_var_1 + 94)
- let cse_var_42: int32 = (cse_var_1 + 95)
- let cse_var_41: int32 = (cse_var_1 + 96)
- let cse_var_40: int32 = (cse_var_1 + 97)
- let cse_var_39: int32 = (cse_var_1 + 98)
- let cse_var_38: int32 = (cse_var_1 + 99)
- let cse_var_37: int32 = (elem_idx*16)
- let cse_var_36: int32 = (cse_var_1 + 86)
- let cse_var_35: int32 = (cse_var_1 + 43)
- let cse_var_34: int32 = (cse_var_1 + 44)
- let cse_var_33: int32 = (cse_var_1 + 45)
- let cse_var_32: int32 = (cse_var_1 + 46)
- let cse_var_31: int32 = (cse_var_1 + 47)
- let cse_var_30: int32 = (cse_var_1 + 48)
- let cse_var_29: int32 = (cse_var_1 + 49)
- let cse_var_28: int32 = (cse_var_1 + 5)
- let cse_var_27: int32 = (cse_var_1 + 50)
- let cse_var_26: int32 = (cse_var_1 + 51)
- let cse_var_25: int32 = (cse_var_1 + 52)
- let cse_var_24: int32 = (cse_var_1 + 53)
- let cse_var_23: int32 = (cse_var_1 + 54)
- let cse_var_22: int32 = (cse_var_1 + 55)
- let cse_var_21: int32 = (cse_var_1 + 56)
- let cse_var_20: int32 = (cse_var_1 + 57)
- let cse_var_19: int32 = (cse_var_1 + 71)
- let cse_var_18: int32 = (cse_var_1 + 7)
- let cse_var_17: int32 = (cse_var_1 + 69)
- let cse_var_16: int32 = (cse_var_1 + 68)
- let cse_var_15: int32 = (cse_var_1 + 67)
- let cse_var_14: int32 = (cse_var_1 + 66)
- let cse_var_13: int32 = (cse_var_1 + 65)
- let cse_var_12: int32 = (cse_var_1 + 64)
- let cse_var_11: int32 = (cse_var_1 + 63)
- let cse_var_10: int32 = (cse_var_1 + 62)
- let cse_var_9: int32 = (cse_var_1 + 61)
- let cse_var_8: int32 = (cse_var_1 + 60)
- let cse_var_7: int32 = (cse_var_1 + 6)
- let cse_var_6: int32 = (cse_var_1 + 59)
- let cse_var_5: int32 = (cse_var_1 + 70)
- let cse_var_4: int32 = (cse_var_1 + 58)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048))
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [256], [])[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, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*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 = ((i.inner*32) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_18: int32 = (cse_var_20 + 1)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_20 + 10)
{
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_132: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
- compute[cse_var_132] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_132]), 0f32)
- }
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -820,7 +487,7 @@ We build the binary and check its correctness and performance.
/workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 2.502 ms
+ Execution time of this operator: 1.882 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 a161cc91f..d6e688f25 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.935** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.936** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.053**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.232**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.218**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.216**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:44.096**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.219**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.211**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.203**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
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 13eccde37..294f487d2 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.41/42.41 result: MeasureResult(costs=(0.0054580131578947375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.575484037399292, timestamp=1653605049.7827628) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 93.78/93.78 result: MeasureResult(costs=(0.0024686733541666663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.754946231842041, timestamp=1653652905.6925685) [('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: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/93.78 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
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f6b8eee2fa2
+ 12: 0x00007f9a19cb4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.76/143.76 result: MeasureResult(costs=(0.00161030436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3760154247283936, timestamp=1653605076.1585646) [('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: 143.73/143.73 result: MeasureResult(costs=(0.0016106633299999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4333069324493408, timestamp=1653652932.1503072) [('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
@@ -2441,7 +2441,7 @@ and measure running time.
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
- Time cost of this operator: 0.001955
+ Time cost of this operator: 0.002051
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 7281f32f9..d30c3d19d 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
@@ -294,10 +294,10 @@ 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 312.0 98.728 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.953 0.934 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.067 0.338 (1, 1, 10, 10, 3) 1 1
- Total_time - 316.02 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.5 98.732 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.142 0.983 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.91 0.285 (1, 1, 10, 10, 3) 1 1
+ Total_time - 319.552 - - - -
@@ -359,10 +359,10 @@ 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 96.65 97.409 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.758 1.772 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.813 0.819 (1, 3, 10, 10, 1) 1 1
- Total_time - 99.221 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 225.5 98.746 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.047 0.896 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.816 0.357 (1, 3, 10, 10, 1) 1 1
+ Total_time - 228.363 - - - -
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 92b510fbc..a079bcfa6 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.882** total execution time for **how_to_work_with_microtvm** files:
+**00:45.898** total execution time for **how_to_work_with_microtvm** files:
-- **00:41.651**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.632**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.201**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.199**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:41.715**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.604**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.193**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.190**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
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 d0e9c305b..98413c3ce 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:12.157** total execution time for **how_to_work_with_relay** files:
+**00:12.310** total execution time for **how_to_work_with_relay** files:
-- **00:09.980**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.959**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.219**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:10.093**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:02.012**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.205**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
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 27db43c1e..a992d87b7 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.732** total execution time for **how_to_work_with_schedules** files:
+**00:05.687** total execution time for **how_to_work_with_schedules** files:
-- **00:02.102**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.142**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.737**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.727**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.315**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.243**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.241**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.225**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.072**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.203**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.721**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.703**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.306**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.243**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.220**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:00.219**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
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 76392d66b..617060f3f 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ 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/tmplfm8mwyy/input0.cc'\nsource_filename = \"/tmp/tmplfm8mwyy/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/tmp4h4jocck/input0.cc'\nsource_filename = \"/tmp/tmp4h4jocck/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 bc775c0d4..7b35236d0 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.664** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.737** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.457**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.206**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.527**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.210**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 341a1599a..07a992f51 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -267,7 +267,7 @@ 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 21.29s!
+ resnet18_v1 inference graph built in 21.54s!
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 7bb18845c..8b5ad9e69 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -303,7 +303,7 @@ 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 14.81s!
+ yolov3-tiny inference graph built in 14.97s!
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 2a3cbadd8..66d436812 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:28.363** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.498** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.952**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.411**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.954**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.543**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
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 9c2007c63..99a7ed84a 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.488** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.551** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.934**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.554**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.004**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.547**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 48452c9e4..b9c730c7a 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:00.999** total execution time for **topic_vta_tutorials** files:
+**00:01.020** total execution time for **topic_vta_tutorials** files:
-- **00:00.506**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.493**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.515**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.505**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 27ffefc85..1d0ccc934 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E
+
@@ -308,7 +308,7 @@ We build the binary and check its correctness and performance.
/workspace/python/tvm/target/target.py:317: 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. "
- Execution time of this operator: 93.862 ms
+ Execution time of this operator: 93.462 ms
@@ -404,7 +404,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -417,11 +417,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 23.258 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 11e8cb73e..604618475 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 498.91625751000447, 'median': 498.82358639999893, 'std': 0.3731100177629365}
+ {'mean': 492.2508833299991, 'median': 491.67398674999845, 'std': 1.3296887953029062}
@@ -494,31 +494,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.50/ 17.50 GFLOPS | Progress: (4/20) | 6.60 s
[Task 1/25] Current/Best: 6.14/ 17.50 GFLOPS | Progress: (8/20) | 9.06 s
[Task 1/25] Current/Best: 11.55/ 22.75 GFLOPS | Progress: (12/20) | 11.52 s
[Task 1/25] Current/Best: 16.70/ 22.78 GFLOPS | Progress: (16/20) | 13.20 s
[Task 1/25] Current/Best: 10.88/ 23.87 GFLOPS | Progress: (20/20) | 14.94 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.26/ 13.05 GFLOPS | Progress: (4/20) | 3.58 s
[Task 2/25] Current/Best: 13.76/ 17.34 GFLOPS | Progress: (8/20) | 4.89 s
[Task 2/25] Current/Best: 21.17/ 21.17 GFLOPS | Progress: (12/20) | 6.24 s
[Task 2/25] Current/Best: 12.04/ 21.17 GFLOPS | Progress: (16/20) | 7.52 s
[Task 2/25] Current/Best: 20.02/ 21.17 GFLOPS | Progress: (20/20) | 9.10 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: 15.58/ 16.89 GFLOPS | Progress: (8/20) | 7.71 s
[Task 3/25] Current/Best: 14.83/ 16.89 GFLOPS | Progress: (12/20) | 9.45 s
[Task 3/25] Current/Best: 7.21/ 23.73 GFLOPS | Progress: (16/20) | 11.36 s
[Task 3/25] Current/Best: 12.12/ 23.73 GFLOPS | Progress: (20/20) | 15.87 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 19.15 GFLOPS | Progress: (4/20) | 2.34 s
[Task 4/25] Current/Best: 6.80/ 19.15 GFLOPS | Progress: (8/20) | 6.64 s
[Task 4/25] Current/Best: 22.45/ 22.45 GFLOPS | Progress: (12/20) | 11.18 s
[Task 4/25] Current/Best: 16.92/ 22.45 GFLOPS | Progress: (16/20) | 13.43 s
[Task 4/25] Current/Best: 13.38/ 22.45 GFLOPS | Progress: (20/20) | 15.33 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.59/ 10.25 GFLOPS | Progress: (4/20) | 2.56 s
[Task 5/25] Current/Best: 11.85/ 12.76 GFLOPS | Progress: (8/20) | 4.63 s
[Task 5/25] Current/Best: 10.64/ 18.03 GFLOPS | Progress: (12/20) | 7.72 s
[Task 5/25] Current/Best: 11.89/ 22.82 GFLOPS | Progress: (16/20) | 9.14 s
[Task 5/25] Current/Best: 12.07/ 22.82 GFLOPS | Progress: (20/20) | 11.01 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.22/ 20.71 GFLOPS | Progress: (4/20) | 3.91 s
[Task 6/25] Current/Best: 19.00/ 20.71 GFLOPS | Progress: (8/20) | 5.68 s
[Task 6/25] Current/Best: 13.17/ 20.71 GFLOPS | Progress: (12/20) | 7.62 s
[Task 6/25] Current/Best: 19.92/ 20.71 GFLOPS | Progress: (16/20) | 9.86 s
[Task 6/25] Current/Best: 3.70/ 20.71 GFLOPS | Progress: (20/20) | 12.43 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.45/ 12.84 GFLOPS | Progress: (4/20) | 3.60 s
[Task 7/25] Current/Best: 19.93/ 20.30 GFLOPS | Progress: (8/20) | 5.15 s
[Task 7/25] Current/Best: 15.22/ 20.30 GFLOPS | Progress: (12/20) | 7.08 s
[Task 7/25] Current/Best: 12.22/ 20.54 GFLOPS | Progress: (16/20) | 9.16 s
[Task 7/25] Current/Best: 6.29/ 21.54 GFLOPS | Progress: (20/20) | 11.65 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 8.46/ 13.37 GFLOPS | Progress: (4/20) | 3.06 s
[Task 8/25] Current/Best: 9.43/ 13.37 GFLOPS | Progress: (8/20) | 8.26 s
[Task 8/25] Current/Best: 12.97/ 13.63 GFLOPS | Progress: (12/20) | 14.67 s
[Task 8/25] Current/Best: 18.69/ 18.69 GFLOPS | Progress: (16/20) | 16.79 s
[Task 8/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (20/20) | 23.52 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.17/ 15.55 GFLOPS | Progress: (4/20) | 18.31 s
[Task 9/25] Current/Best: 22.02/ 22.02 GFLOPS | Progress: (8/20) | 20.15 s
[Task 9/25] Current/Best: 8.21/ 22.02 GFLOPS | Progress: (12/20) | 22.60 s
[Task 9/25] Current/Best: 17.75/ 22.02 GFLOPS | Progress: (16/20) | 25.38 s
[Task 9/25] Current/Best: 8.91/ 22.02 GFLOPS | Progress: (20/20) | 33.45 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (4/20) | 2.65 s
[Task 10/25] Current/Best: 15.52/ 18.19 GFLOPS | Progress: (8/20) | 4.23 s
[Task 10/25] Current/Best: 12.33/ 19.12 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 19.14/ 20.08 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.89/ 20.08 GFLOPS | Progress: (20/20
) | 8.41 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.12/ 18.12 GFLOPS | Progress: (4/20) | 3.24 s
[Task 11/25] Current/Best: 16.68/ 18.12 GFLOPS | Progress: (8/20) | 5.95 s
[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 7.98 s
[Task 11/25] Current/Best: 13.36/ 21.06 GFLOPS | Progress: (16/20) | 10.71 s
[Task 11/25] Current/Best: 19.46/ 21.37 GFLOPS | Progress: (20/20) | 12.73 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.15 GFLOPS | Progress: (4/20) | 5.32 s
[Task 12/25] Current/Best: 5.10/ 18.15 GFLOPS | Progress: (8/20) | 9.00 s
[Task 12/25] Current/Best: 18.86/ 18.94 GFLOPS | Progress: (12/20) | 10.98 s
[Task 12/25] Current/Best: 15.56/ 18.94 GFLOPS | Progress: (16/20) | 13.72 s
[Task 12/25] Current/Best: 15.15/ 18.94 GFLOPS | Progress: (20/20) | 15.65 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.05/ 17.26 GFLOPS | Progress: (4/20) | 3.58 s
[Task 13/25] Current/Best: 16.00/ 20.84 GFLOPS | Progress: (8/20) | 6.02 s
[Task 13/25] Current/Best: 19.72/ 21.56 GFLOPS | Progress: (12/20) | 8.89 s
[Task 13/25] Current/Best: 12.21/ 21.56 GFLOPS | Progress: (16/20) | 12.31 s
[Task 13/25] Current/Best: 18.59/ 21.56 GFLOPS | Progress: (20/20) | 14.56 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 12.56/ 13.38 GFLOPS | Progress: (4/20) | 3.29 s
[Task 14/25] Current/Best: 6.11/ 13.38 GFLOPS | Progress: (8/20) | 5.50 s
[Task 14/25] Current/Best: 20.95/ 20.95 GFLOPS | Progress: (12/20) | 8.05 s
[Task 14/25] Current/Best: 16.30/ 20.95 GFLOPS | Progress: (16/20) | 9.98 s
[Task 14/25] Current/Best: 16.94/ 20.95 GFLOPS | Progress: (20/20) | 11.75 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/20) | 5.91 s
[Task 1/25] Current/Best: 6.16/ 17.55 GFLOPS | Progress: (8/20) | 8.79 s
[Task 1/25] Current/Best: 11.57/ 22.90 GFLOPS | Progress: (12/20) | 11.17 s
[Task 1/25] Current/Best: 16.90/ 22.90 GFLOPS | Progress: (16/20) | 12.84 s
[Task 1/25] Current/Best: 11.63/ 23.90 GFLOPS | Progress: (20/20) | 14.55 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/ 12.84 GFLOPS | Progress: (4/20) | 3.67 s
[Task 2/25] Current/Best: 14.27/ 18.48 GFLOPS | Progress: (8/20) | 4.94 s
[Task 2/25] Current/Best: 21.23/ 21.23 GFLOPS | Progress: (12/20) | 6.28 s
[Task 2/25] Current/Best: 12.17/ 21.23 GFLOPS | Progress: (16/20) | 7.51 s
[Task 2/25] Current/Best: 19.25/ 21.23 GFLOPS | Progress: (20/20) | 9.05 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) | 5.76 s
[Task 3/25] Current/Best: 15.65/ 16.91 GFLOPS | Progress: (8/20) | 7.66 s
[Task 3/25] Current/Best: 14.96/ 16.91 GFLOPS | Progress: (12/20) | 9.35 s
[Task 3/25] Current/Best: 7.21/ 23.83 GFLOPS | Progress: (16/20) | 11.24 s
[Task 3/25] Current/Best: 12.47/ 23.83 GFLOPS | Progress: (20/20) | 15.73 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.37 GFLOPS | Progress: (4/20) | 2.27 s
[Task 4/25] Current/Best: 6.87/ 20.37 GFLOPS | Progress: (8/20) | 6.57 s
[Task 4/25] Current/Best: 22.56/ 22.56 GFLOPS | Progress: (12/20) | 11.04 s
[Task 4/25] Current/Best: 15.85/ 22.56 GFLOPS | Progress: (16/20) | 13.23 s
[Task 4/25] Current/Best: 13.53/ 22.56 GFLOPS | Progress: (20/20) | 15.25 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.72/ 10.37 GFLOPS | Progress: (4/20) | 2.48 s
[Task 5/25] Current/Best: 11.73/ 11.77 GFLOPS | Progress: (8/20) | 4.52 s
[Task 5/25] Current/Best: 11.88/ 18.03 GFLOPS | Progress: (12/20) | 7.61 s
[Task 5/25] Current/Best: 11.67/ 22.44 GFLOPS | Progress: (16/20) | 9.02 s
[Task 5/25] Current/Best: 12.07/ 22.44 GFLOPS | Progress: (20/20) | 10.87 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.25/ 20.74 GFLOPS | Progress: (4/20) | 3.88 s
[Task 6/25] Current/Best: 18.86/ 20.74 GFLOPS | Progress: (8/20) | 5.64 s
[Task 6/25] Current/Best: 13.26/ 20.74 GFLOPS | Progress: (12/20) | 7.57 s
[Task 6/25] Current/Best: 19.77/ 20.74 GFLOPS | Progress: (16/20) | 9.80 s
[Task 6/25] Current/Best: 3.70/ 20.74 GFLOPS | Progress: (20/20) | 12.33 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 9.95/ 12.93 GFLOPS | Progress: (4/20) | 3.54 s
[Task 7/25] Current/Best: 20.15/ 21.09 GFLOPS | Progress: (8/20) | 5.04 s
[Task 7/25] Current/Best: 16.22/ 21.09 GFLOPS | Progress: (12/20) | 6.92 s
[Task 7/25] Current/Best: 12.25/ 21.09 GFLOPS | Progress: (16/20) | 8.97 s
[Task 7/25] Current/Best: 6.29/ 21.86 GFLOPS | Progress: (20/20) | 11.40 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.62/ 13.71 GFLOPS | Progress: (4/20) | 2.83 s
[Task 8/25] Current/Best: 9.36/ 13.71 GFLOPS | Progress: (8/20) | 7.60 s
[Task 8/25] Current/Best: 12.57/ 13.71 GFLOPS | Progress: (12/20) | 13.66 s
[Task 8/25] Current/Best: 18.83/ 18.83 GFLOPS | Progress: (16/20) | 15.79 s
[Task 8/25] Current/Best: 19.31/ 19.31 GFLOPS | Progress: (20/20) | 22.23 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.36/ 15.85 GFLOPS | Progress: (4/20) | 17.41 s
[Task 9/25] Current/Best: 22.77/ 22.77 GFLOPS | Progress: (8/20) | 19.16 s
[Task 9/25] Current/Best: 8.29/ 22.77 GFLOPS | Progress: (12/20) | 21.53 s
[Task 9/25] Current/Best: 17.94/ 22.77 GFLOPS | Progress: (16/20) | 24.08 s
[Task 9/25] Current/Best: 9.02/ 22.77 GFLOPS | Progress: (20/20) | 31.63 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.75/ 17.75 GFLOPS | Progress: (4/20) | 2.49 s
[Task 10/25] Current/Best: 15.60/ 17.75 GFLOPS | Progress: (8/20) | 4.05 s
[Task 10/25] Current/Best: 12.58/ 18.80 GFLOPS | Progress: (12/20) | 5.55 s
[Task 10/25] Current/Best: 18.79/ 20.39 GFLOPS | Progress: (16/20) | 6.65 s
[Task 10/25] Current/Best: 8.84/ 20.39 GFLOPS | Progress: (20/20
) | 8.16 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 10.87/ 18.08 GFLOPS | Progress: (4/20) | 3.21 s
[Task 11/25] Current/Best: 16.89/ 18.08 GFLOPS | Progress: (8/20) | 5.91 s
[Task 11/25] Current/Best: 16.60/ 18.08 GFLOPS | Progress: (12/20) | 7.92 s
[Task 11/25] Current/Best: 13.29/ 21.01 GFLOPS | Progress: (16/20) | 10.70 s
[Task 11/25] Current/Best: 19.52/ 21.45 GFLOPS | Progress: (20/20) | 12.71 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.04 GFLOPS | Progress: (4/20) | 5.20 s
[Task 12/25] Current/Best: 5.35/ 18.04 GFLOPS | Progress: (8/20) | 8.87 s
[Task 12/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 10.83 s
[Task 12/25] Current/Best: 15.67/ 19.28 GFLOPS | Progress: (16/20) | 13.57 s
[Task 12/25] Current/Best: 15.01/ 19.28 GFLOPS | Progress: (20/20) | 15.51 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.57/ 17.22 GFLOPS | Progress: (4/20) | 3.55 s
[Task 13/25] Current/Best: 16.06/ 21.14 GFLOPS | Progress: (8/20) | 5.97 s
[Task 13/25] Current/Best: 19.48/ 21.60 GFLOPS | Progress: (12/20) | 8.86 s
[Task 13/25] Current/Best: 12.28/ 21.60 GFLOPS | Progress: (16/20) | 12.27 s
[Task 13/25] Current/Best: 18.75/ 21.60 GFLOPS | Progress: (20/20) | 14.54 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.50/ 13.50 GFLOPS | Progress: (4/20) | 3.24 s
[Task 14/25] Current/Best: 6.08/ 13.50 GFLOPS | Progress: (8/20) | 5.42 s
[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 7.94 s
[Task 14/25] Current/Best: 17.16/ 20.49 GFLOPS | Progress: (16/20) | 9.81 s
[Task 14/25] Current/Best: 17.16/ 20.49 GFLOPS | Progress: (20/20) | 11.57 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 16.03/ 17.59 GFLOPS | Progress: (4/20) | 2.62 s
[Task 15/25] Current/Best: 14.39/ 18.08 GFLOPS | Progress: (8/20) | 4.14 s
[Task 15/25] Current/Best: 10.37/ 22.21 GFLOPS | Progress: (12/20) | 6.27 s
[Task 15/25] Current/Best: 20.10/ 22.21 GFLOPS | Progress: (16/20) | 9.20 s
[Task 15/25] Current/Best: 9.70/ 22.21 GFLOPS | Progress: (20/20) | 10.36 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (4/20) | 2.86 s
[Task 16/25] Current/Best: 3.03/ 20.55 GFLOPS | Progress: (8/20) | 4.46 s
[Task 16/25] Current/Best: 19.35/ 20.55 GFLOPS | Progress: (12/20) | 5.67 s
[Task 16/25] Current/Best: 18.32/ 20.55 GFLOPS | Progress: (16/20) | 7.00 s
[Task 16/25] Current/Best: 10.03/ 22.26 GFLOPS | Progress: (20/20) | 9.03 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.75/ 18.41 GFLOPS | Progress: (4/20) | 4.64 s
[Task 17/25] Current/Best: 14.47/ 23.41 GFLOPS | Progress: (8/20) | 7.40 s
[Task 17/25] Current/Best: 16.68/ 23.41 GFLOPS | Progress: (12/20) | 9.46 s
[Task 17/25] Current/Best: 16.54/ 23.41 GFLOPS | Progress: (16/20) | 11.58 s
[Task 17/25] Current/Best: 10.06/ 23.41 GFLOPS | Progress: (20/20) | 13.70 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.17/ 17.92 GFLOPS | Progress: (4/20) | 3.64 s
[Task 18/25] Current/Best: 10.55/ 19.43 GFLOPS | Progress: (8/20) | 7.06 s
[Task 18/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (12/20) | 8.97 s
[Task 18/25] Current/Best: 10.02/ 19.54 GFLOPS | Progress: (16/20) | 12.54 s
[Task 18/25] Current/Best: 20.53/ 20.53 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: 6.70/ 20.13 GFLOPS | Progress: (4/20) | 6.02 s
[Task 19/25] Current/Best: 2.59/ 20.13 GFLOPS | Progress: (8/20) | 9.36 s
[Task 19/25] Current/Best: 14.66/ 21.01 GFLOPS | Progress: (12/20) | 12.24 s
[Task 19/25] Current/Best: 15.51/ 21.01 GFLOPS | Progress: (16/20) | 15.11 s
[Task 19/25] Current/Best: 2.68/ 23.16 GFLOPS | Progress: (20/20) | 17.92 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.44/ 15.34 GFLOPS | Progress: (4/20) | 3.22 s
[Task 20/25] Current/Best: 10.08/ 15.34 GFLOPS | Progress: (8/20) | 6.64 s
[Task 20/25] Current/Best: 2.28/ 15.81 GFLOPS | Progress: (12/20) | 10.57 s
[Task 20/25] Current/Best: 12.43/ 15.81 GFLOPS | Progress: (16/20) | 14.16 s Done.
-
[Task 20/25] Current/Best: 11.63/ 22.10 GFLOPS | Progress: (20/20) | 16.27 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.62 GFLOPS | Progress: (4/20) | 3.16 s
[Task 21/25] Current/Best: 14.58/ 17.62 GFLOPS | Progress: (8/20) | 4.72 s
[Task 21/25] Current/Best: 1.61/ 17.62 GFLOPS | Progress: (12/20) | 6.83 s
[Task 21/25] Current/Best: 18.03/ 18.03 GFLOPS | Progress: (16/20) | 10.25 s
[Task 21/25] Current/Best: 4.45/ 18.03 GFLOPS | Progress: (20/20) | 17.41 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) | 2.63 s
[Task 22/25] Current/Best: 8.72/ 21.16 GFLOPS | Progress: (8/20) | 4.61 s
[Task 22/25] Current/Best: 20.02/ 21.16 GFLOPS | Progress: (12/20) | 6.90 s
[Task 22/25] Current/Best: 15.22/ 21.16 GFLOPS | Progress: (16/20) | 8.95 s
[Task 22/25] Current/Best: 13.75/ 21.16 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: 17.47/ 20.60 GFLOPS | Progress: (4/20) | 3.16 s
[Task 23/25] Current/Best: 15.91/ 20.60 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 20.84/ 21.58 GFLOPS | Progress: (12/20) | 8.33 s
[Task 23/25] Current/Best: 5.97/ 21.58 GFLOPS | Progress: (16/20) | 15.41 s
[Task 23/25] Current/Best: 7.66/ 21.58 GFLOPS | Progress: (20/20) | 19.64 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.57/ 8.57 GFLOPS | Progress: (4/20) | 13.63 s
[Task 24/25] Current/Best: 3.59/ 8.57 GFLOPS | Progress: (8/20) | 29.14 s
[Task 24/25] Current/Best: 3.04/ 8.57 GFLOPS | Progress: (12/20) | 52.16 s
[Task 24/25] Current/Best: 6.85/ 8.57 GFLOPS | Progress: (16/20) | 57.79 s
[Task 24/25] Current/Best: 3.08/ 8.69 GFLOPS | Progress: (20/20) | 63.97 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 15/25] Current/Best: 16.14/ 17.65 GFLOPS | Progress: (4/20) | 2.58 s
[Task 15/25] Current/Best: 14.38/ 18.08 GFLOPS | Progress: (8/20) | 4.04 s
[Task 15/25] Current/Best: 10.28/ 21.88 GFLOPS | Progress: (12/20) | 6.17 s
[Task 15/25] Current/Best: 20.43/ 21.88 GFLOPS | Progress: (16/20) | 9.15 s
[Task 15/25] Current/Best: 9.71/ 21.88 GFLOPS | Progress: (20/20) | 10.27 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.01/ 20.01 GFLOPS | Progress: (4/20) | 2.82 s
[Task 16/25] Current/Best: 3.02/ 20.01 GFLOPS | Progress: (8/20) | 4.41 s
[Task 16/25] Current/Best: 19.14/ 20.01 GFLOPS | Progress: (12/20) | 5.61 s
[Task 16/25] Current/Best: 17.88/ 20.01 GFLOPS | Progress: (16/20) | 6.93 s
[Task 16/25] Current/Best: 9.93/ 22.60 GFLOPS | Progress: (20/20) | 8.95 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.20/ 18.25 GFLOPS | Progress: (4/20) | 4.57 s
[Task 17/25] Current/Best: 14.45/ 23.04 GFLOPS | Progress: (8/20) | 7.39 s
[Task 17/25] Current/Best: 16.85/ 23.04 GFLOPS | Progress: (12/20) | 9.44 s
[Task 17/25] Current/Best: 16.47/ 23.04 GFLOPS | Progress: (16/20) | 11.56 s
[Task 17/25] Current/Best: 9.63/ 23.04 GFLOPS | Progress: (20/20) | 13.66 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.29/ 18.03 GFLOPS | Progress: (4/20) | 3.57 s
[Task 18/25] Current/Best: 10.52/ 19.56 GFLOPS | Progress: (8/20) | 6.98 s
[Task 18/25] Current/Best: 19.37/ 19.56 GFLOPS | Progress: (12/20) | 8.87 s
[Task 18/25] Current/Best: 10.02/ 19.56 GFLOPS | Progress: (16/20) | 12.45 s
[Task 18/25] Current/Best: 20.16/ 20.16 GFLOPS | Progress: (20/20) | 13.98 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.25/ 20.53 GFLOPS | Progress: (4/20) | 5.87 s
[Task 19/25] Current/Best: 2.60/ 20.53 GFLOPS | Progress: (8/20) | 9.16 s
[Task 19/25] Current/Best: 20.30/ 21.84 GFLOPS | Progress: (12/20) | 11.96 s
[Task 19/25] Current/Best: 14.33/ 21.97 GFLOPS | Progress: (16/20) | 14.85 s
[Task 19/25] Current/Best: 2.71/ 23.85 GFLOPS | Progress: (20/20) | 17.66 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.44/ 15.33 GFLOPS | Progress: (4/20) | 3.22 s
[Task 20/25] Current/Best: 9.69/ 15.33 GFLOPS | Progress: (8/20) | 6.67 s
[Task 20/25] Current/Best: 2.31/ 15.33 GFLOPS | Progress: (12/20) | 10.48 s
[Task 20/25] Current/Best: 12.24/ 15.33 GFLOPS | Progress: (16/20) | 14.17 s
[Task 20/25] Current/Best: 12.53/ 21.90 GFLOPS | Progress: (20/20) | 16.28 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 1.53/ 2.74 GFLOPS | Progress: (4/20) | 32.88 s
[Task 25/25] Current/Best: 5.87/ 8.51 GFLOPS | Progress: (8/20) | 358.28 s
[Task 25/25] Current/Best: 6.07/ 8.51 GFLOPS | Progress: (12/20) | 386.21 s
[Task 25/25] Current/Best: 5.87/ 9.40 GFLOPS | Progress: (16/20) | 387.90 s
[Task 25/25] Current/Best: 2.94/ 9.40 GFLOPS | Progress: (20/20) | 407.98 s
+
[Task 21/25] Current/Best: 6.39/ 17.72 GFLOPS | Progress: (4/20) | 3.11 s
[Task 21/25] Current/Best: 14.64/ 17.72 GFLOPS | Progress: (8/20) | 4.67 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.75 s
[Task 21/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (16/20) | 10.12 s
[Task 21/25] Current/Best: 4.45/ 17.99 GFLOPS | Progress: (20/20) | 17.11 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) | 2.58 s
[Task 22/25] Current/Best: 8.66/ 21.66 GFLOPS | Progress: (8/20) | 4.55 s
[Task 22/25] Current/Best: 20.05/ 21.66 GFLOPS | Progress: (12/20) | 6.87 s
[Task 22/25] Current/Best: 15.50/ 21.66 GFLOPS | Progress: (16/20) | 8.92 s
[Task 22/25] Current/Best: 14.38/ 21.66 GFLOPS | Progress: (20/20) | 10.63 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.76/ 20.79 GFLOPS | Progress: (4/20) | 3.13 s
[Task 23/25] Current/Best: 14.26/ 20.79 GFLOPS | Progress: (8/20) | 6.48 s
[Task 23/25] Current/Best: 21.05/ 21.67 GFLOPS | Progress: (12/20) | 8.25 s
[Task 23/25] Current/Best: 6.44/ 21.67 GFLOPS | Progress: (16/20) | 15.18 s
[Task 23/25] Current/Best: 7.90/ 21.67 GFLOPS | Progress: (20/20) | 19.35 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.63/ 8.63 GFLOPS | Progress: (4/20) | 13.55 s
[Task 24/25] Current/Best: 2.17/ 8.63 GFLOPS | Progress: (8/20) | 29.87 s
[Task 24/25] Current/Best: 4.61/ 8.63 GFLOPS | Progress: (12/20) | 53.09 s
[Task 24/25] Current/Best: 6.25/ 9.05 GFLOPS | Progress: (16/20) | 58.35 s
[Task 24/25] Current/Best: 3.44/ 9.05 GFLOPS | Progress: (20/20) | 64.14 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+ Done.
+
[Task 25/25] Current/Best: 1.55/ 2.74 GFLOPS | Progress: (4/20) | 30.50 s
[Task 25/25] Current/Best: 6.17/ 8.88 GFLOPS | Progress: (8/20) | 318.41 s
[Task 25/25] Current/Best: 6.10/ 8.88 GFLOPS | Progress: (12/20) | 346.82 s
[Task 25/25] Current/Best: 5.99/ 9.23 GFLOPS | Progress: (16/20) | 348.63 s
[Task 25/25] Current/Best: 2.88/ 9.72 GFLOPS | Progress: (20/20) | 368.58 s
The output from this tuning process will look something like this:
@@ -660,8 +660,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 409.9049065999998, 'median': 409.9493076500039, 'std': 1.4443281286747947}
- unoptimized: {'mean': 498.91625751000447, 'median': 498.82358639999893, 'std': 0.3731100177629365}
+ optimized: {'mean': 409.05647228000134, 'median': 409.0174518499907, 'std': 0.7912409888342841}
+ unoptimized: {'mean': 492.2508833299991, 'median': 491.67398674999845, 'std': 1.3296887953029062}
@@ -681,7 +681,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 16 minutes 43.297 seconds)
+ **Total running time of the script:** ( 15 minutes 51.927 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 d37d34ea1..041626438 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -244,7 +244,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.274e-07 secs/op
+ 1.287e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 33d95a3de..5e166783b 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xd3bdf80)), stage(b, placeholder(b, 0x2a8c09f0)), 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 [...]
+ [stage(a, placeholder(a, 0x27d112e0)), stage(b, placeholder(b, 0xee8cd30)), 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 4b71f98d7..689c95be9 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**19:59.963** total execution time for **tutorial** files:
+**18:41.140** total execution time for **tutorial** files:
-- **16:43.297**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:23.258**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **01:01.446**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:26.021**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.530**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.293**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.714**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.219**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.048**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.047**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.046**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.044**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **15:51.927**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:00.926**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:56.111**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:25.875**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:24.279**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.045**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.689**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.176**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.027**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.027**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.027**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 4d7c9017a..817eacf6f 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -252,8 +252,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
- naive: 0.000008
+ Numpy running time: 0.000011
+ naive: 0.000006
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.820949999768345e-06 1.0
- naive 8.443799999999999e-06 1.07963866285427
- parallel 7.0503e-06 0.9014633772379095
- vector 2.4644499999999998e-05 3.151087783546751
+ numpy 1.0507160000088334e-05 1.0
+ naive 5.9151e-06 0.5629589727338569
+ parallel 7.010599999999999e-06 0.6672212091508134
+ vector 2.4501600000000003e-05 2.3318955835634
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019042
+ Numpy running time: 0.018096
@@ -897,7 +897,7 @@ optimizations.
/workspace/python/tvm/target/target.py:317: 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: 3.432912
+ none: 3.433583
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.308167
+ blocking: 0.293220
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.339106
+ vectorization: 0.331327
@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], []),
@@ -1160,7 +1160,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119706
+ loop permutation: 0.112196
@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], []),
@@ -1257,7 +1257,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110581
+ array packing: 0.108316
@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], []),
@@ -1348,7 +1348,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.113189
+ block caching: 0.110597
@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], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145316
+ parallelization: 0.144215
@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], []),
@@ -1511,13 +1511,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4329122497999998 1.0
- blocking 0.30816739330000004 0.08976850291409394
- vectorization 0.3391055713 0.09878072803048088
- loop permutation 0.1197055175 0.03486996135918534
- array packing 0.1105813771 0.03221211876488903
- block caching 0.11318945949999999 0.03297184759284027
- parallelization 0.14531579109999998 0.042330179313050026
+ none 3.4335830831000003 1.0
+ blocking 0.2932196695 0.08539757518704556
+ vectorization 0.3313273432 0.09649609028853384
+ loop permutation 0.1121955751 0.032675945909747595
+ array packing 0.10831572020000002 0.03154597328170883
+ block caching 0.1105971797 0.032210427714522545
+ parallelization 0.14421537169999998 0.04200142189942163
@@ -1554,7 +1554,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 1.446 seconds)
+ **Total running time of the script:** ( 1 minutes 0.926 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 65126e122..a4f228e72 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-4a769c1da3fef695bb865a1ade91236bbd28f37a
+aaee8aa441ba9be3934dbfa358767d54f2b2e159
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index 8def54396..3e99f9a95 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -551,7 +551,6 @@ class:['truck 0.9266'] left:471 right:83 top:689 bottom:169
class:['bicycle 0.9984'] left:111 right:113 top:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.451 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 585aae1a2..5d32145cc 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipa91db0de-31a0-4a62-a78b-f9d973d9753a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipf950dfa4-db27-4e8f-a5a9-740ed2e4ca4d 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 76acfa304..cc1b5f8fe 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,47 +406,43 @@ 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<07:23, 98.1kB/s]
- 0%| | 48.0k/41.5M [00:00<04:39, 155kB/s]
- 0%| | 96.0k/41.5M [00:00<03:19, 218kB/s]
- 0%| | 184k/41.5M [00:00<02:06, 344kB/s]
- 1%| | 304k/41.5M [00:00<01:29, 483kB/s]
- 1%|1 | 576k/41.5M [00:01<00:48, 881kB/s]
- 2%|2 | 880k/41.5M [00:01<00:35, 1.20MB/s]
- 4%|4 | 1.73M/41.5M [00:01<00:16, 2.54MB/s]
- 8%|7 | 3.20M/41.5M [00:01<00:08, 4.63MB/s]
- 11%|#1 | 4.70M/41.5M [00:01<00:06, 6.07MB/s]
- 15%|#4 | 6.18M/41.5M [00:01<00:05, 7.05MB/s]
- 18%|#8 | 7.66M/41.5M [00:02<00:04, 7.72MB/s]
- 22%|##2 | 9.15M/41.5M [00:02<00:04, 8.18MB/s]
- 26%|##5 | 10.6M/41.5M [00:02<00:03, 8.51MB/s]
- 29%|##9 | 12.1M/41.5M [00:02<00:03, 8.75MB/s]
- 33%|###2 | 13.6M/41.5M [00:02<00:03, 8.90MB/s]
- 36%|###6 | 15.1M/41.5M [00:02<00:03, 9.01MB/s]
- 40%|###9 | 16.6M/41.5M [00:03<00:02, 9.09MB/s]
- 44%|####3 | 18.1M/41.5M [00:03<00:02, 10.4MB/s]
- 46%|####6 | 19.2M/41.5M [00:03<00:02, 10.7MB/s]
- 49%|####8 | 20.3M/41.5M [00:03<00:02, 9.90MB/s]
- 51%|#####1 | 21.3M/41.5M [00:03<00:02, 8.70MB/s]
- 54%|#####4 | 22.5M/41.5M [00:03<00:02, 9.63MB/s]
- 57%|#####7 | 23.7M/41.5M [00:03<00:01, 10.2MB/s]
- 60%|#####9 | 24.7M/41.5M [00:03<00:01, 9.41MB/s]
- 62%|######1 | 25.6M/41.5M [00:04<00:02, 8.22MB/s]
- 65%|######5 | 27.0M/41.5M [00:04<00:01, 9.38MB/s]
- 68%|######7 | 28.2M/41.5M [00:04<00:01, 9.49MB/s]
- 70%|####### | 29.1M/41.5M [00:04<00:01, 9.48MB/s]
- 72%|#######2 | 30.0M/41.5M [00:04<00:01, 8.21MB/s]
- 76%|#######5 | 31.4M/41.5M [00:04<00:01, 9.74MB/s]
- 78%|#######8 | 32.6M/41.5M [00:04<00:00, 10.3MB/s]
- 81%|######## | 33.6M/41.5M [00:04<00:00, 9.41MB/s]
- 83%|########3 | 34.5M/41.5M [00:05<00:00, 8.20MB/s]
- 86%|########6 | 35.9M/41.5M [00:05<00:00, 9.60MB/s]
- 89%|########9 | 37.0M/41.5M [00:05<00:00, 10.1MB/s]
- 92%|#########1| 38.0M/41.5M [00:05<00:00, 9.29MB/s]
- 94%|#########3| 39.0M/41.5M [00:05<00:00, 8.11MB/s]
- 97%|#########7| 40.3M/41.5M [00:05<00:00, 9.59MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 10.2MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 7.56MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:35, 95.5kB/s]
+ 0%| | 40.0k/41.5M [00:00<05:52, 123kB/s]
+ 0%| | 88.0k/41.5M [00:00<03:40, 197kB/s]
+ 0%| | 160k/41.5M [00:00<02:30, 288kB/s]
+ 1%| | 336k/41.5M [00:00<01:17, 559kB/s]
+ 1%|1 | 632k/41.5M [00:01<00:44, 965kB/s]
+ 3%|2 | 1.24M/41.5M [00:01<00:22, 1.88MB/s]
+ 6%|6 | 2.49M/41.5M [00:01<00:11, 3.70MB/s]
+ 10%|9 | 3.96M/41.5M [00:01<00:07, 5.32MB/s]
+ 13%|#3 | 5.43M/41.5M [00:01<00:05, 6.43MB/s]
+ 17%|#6 | 6.90M/41.5M [00:01<00:05, 7.20MB/s]
+ 20%|## | 8.37M/41.5M [00:02<00:04, 7.72MB/s]
+ 24%|##3 | 9.84M/41.5M [00:02<00:04, 8.09MB/s]
+ 27%|##7 | 11.3M/41.5M [00:02<00:03, 8.35MB/s]
+ 31%|### | 12.8M/41.5M [00:02<00:03, 8.51MB/s]
+ 34%|###4 | 14.2M/41.5M [00:02<00:03, 8.65MB/s]
+ 38%|###7 | 15.7M/41.5M [00:02<00:02, 9.76MB/s]
+ 40%|#### | 16.7M/41.5M [00:02<00:02, 9.82MB/s]
+ 43%|####2 | 17.7M/41.5M [00:03<00:02, 9.10MB/s]
+ 45%|####4 | 18.7M/41.5M [00:03<00:02, 8.13MB/s]
+ 49%|####8 | 20.1M/41.5M [00:03<00:02, 8.40MB/s]
+ 52%|#####2 | 21.6M/41.5M [00:03<00:02, 8.57MB/s]
+ 56%|#####5 | 23.1M/41.5M [00:03<00:02, 8.66MB/s]
+ 59%|#####9 | 24.5M/41.5M [00:03<00:02, 8.74MB/s]
+ 63%|######2 | 26.0M/41.5M [00:04<00:01, 8.79MB/s]
+ 66%|######6 | 27.5M/41.5M [00:04<00:01, 8.83MB/s]
+ 70%|######9 | 28.9M/41.5M [00:04<00:01, 8.86MB/s]
+ 73%|#######3 | 30.4M/41.5M [00:04<00:01, 8.88MB/s]
+ 77%|#######6 | 31.9M/41.5M [00:04<00:01, 8.90MB/s]
+ 80%|######## | 33.3M/41.5M [00:05<00:00, 8.91MB/s]
+ 84%|########3 | 34.8M/41.5M [00:05<00:00, 8.92MB/s]
+ 87%|########7 | 36.3M/41.5M [00:05<00:00, 9.68MB/s]
+ 91%|######### | 37.7M/41.5M [00:05<00:00, 10.5MB/s]
+ 93%|#########3| 38.8M/41.5M [00:05<00:00, 9.62MB/s]
+ 96%|#########5| 39.7M/41.5M [00:05<00:00, 8.94MB/s]
+ 98%|#########8| 40.7M/41.5M [00:05<00:00, 8.05MB/s]
+100%|##########| 41.5M/41.5M [00:05<00:00, 7.40MB/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 001703794..f7cfeb893 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 13.840 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.955 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download 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 3050f4dcf..2dac8a1c9 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,10 +387,10 @@ 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]
- 10%|# | 4.68M/44.7M [00:00<00:00, 49.0MB/s]
- 21%|## | 9.36M/44.7M [00:00<00:00, 47.9MB/s]
- 72%|#######1 | 32.1M/44.7M [00:00<00:00, 131MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 128MB/s]
+ 14%|#4 | 6.38M/44.7M [00:00<00:00, 66.8MB/s]
+ 29%|##8 | 12.8M/44.7M [00:00<00:00, 64.0MB/s]
+ 86%|########6 | 38.6M/44.7M [00:00<00:00, 156MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 142MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index e7c23d814..ea7a1d57d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.298 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.208 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 5cfee2ab5..924f14393 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<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>05:48.423</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:10.845</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:13.840</strong>: <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></li>
-<li><p><strong>01:02.451</strong>: <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></li>
-<li><p><strong>01:00.298</strong>: <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></li>
-<li><p><strong>00:33.552</strong>: <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></li>
-<li><p><strong>00:29.681</strong>: <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></li>
-<li><p><strong>00:24.067</strong>: <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></li>
-<li><p><strong>00:21.246</strong>: <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></li>
-<li><p><strong>00:21.123</strong>: <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></li>
-<li><p><strong>00:19.486</strong>: <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></li>
-<li><p><strong>00:02.679</strong>: <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></li>
+<li><p><strong>01:04.955</strong>: <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></li>
+<li><p><strong>01:02.208</strong>: <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></li>
+<li><p><strong>00:55.037</strong>: <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></li>
+<li><p><strong>00:29.385</strong>: <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></li>
+<li><p><strong>00:23.690</strong>: <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></li>
+<li><p><strong>00:20.742</strong>: <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></li>
+<li><p><strong>00:20.583</strong>: <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></li>
+<li><p><strong>00:18.747</strong>: <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></li>
+<li><p><strong>00:13.087</strong>: <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></li>
+<li><p><strong>00:02.410</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index c4d502288..f55a9036e 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -627,7 +627,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 14.9208 14.8962 15.2210 14.7275 0.1403
+ 15.7769 15.5907 17.3624 15.4783 0.5460
</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 801609178..04862354b 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,39 +409,13 @@ 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]
- 2%|2 | 3.56M/170M [00:00<00:04, 37.0MB/s]
- 5%|4 | 7.88M/170M [00:00<00:04, 41.4MB/s]
- 8%|8 | 14.4M/170M [00:00<00:03, 53.1MB/s]
- 12%|#2 | 21.1M/170M [00:00<00:02, 59.7MB/s]
- 16%|#5 | 26.8M/170M [00:00<00:02, 57.9MB/s]
- 19%|#9 | 32.3M/170M [00:00<00:02, 57.5MB/s]
- 22%|##2 | 37.8M/170M [00:00<00:02, 56.3MB/s]
- 25%|##5 | 43.2M/170M [00:00<00:02, 56.4MB/s]
- 29%|##8 | 48.6M/170M [00:01<00:02, 42.6MB/s]
- 32%|###1 | 53.5M/170M [00:01<00:02, 44.6MB/s]
- 34%|###4 | 58.1M/170M [00:01<00:02, 45.4MB/s]
- 38%|###7 | 63.8M/170M [00:01<00:02, 49.2MB/s]
- 40%|#### | 68.7M/170M [00:01<00:02, 43.9MB/s]
- 43%|####3 | 73.2M/170M [00:01<00:02, 43.5MB/s]
- 46%|####5 | 77.5M/170M [00:01<00:02, 43.9MB/s]
- 49%|####8 | 82.7M/170M [00:01<00:01, 46.8MB/s]
- 52%|#####1 | 88.0M/170M [00:01<00:01, 49.1MB/s]
- 55%|#####4 | 92.8M/170M [00:02<00:01, 42.2MB/s]
- 57%|#####7 | 97.0M/170M [00:02<00:01, 42.8MB/s]
- 61%|###### | 103M/170M [00:02<00:01, 48.0MB/s]
- 64%|######4 | 109M/170M [00:02<00:01, 52.6MB/s]
- 67%|######7 | 114M/170M [00:02<00:01, 49.5MB/s]
- 71%|####### | 121M/170M [00:02<00:00, 53.6MB/s]
- 74%|#######4 | 126M/170M [00:02<00:00, 51.7MB/s]
- 77%|#######7 | 131M/170M [00:02<00:00, 46.4MB/s]
- 80%|#######9 | 135M/170M [00:02<00:00, 45.2MB/s]
- 83%|########3 | 141M/170M [00:03<00:00, 48.9MB/s]
- 86%|########6 | 147M/170M [00:03<00:00, 51.4MB/s]
- 89%|########9 | 152M/170M [00:03<00:00, 49.3MB/s]
- 92%|#########2| 157M/170M [00:03<00:00, 47.7MB/s]
- 95%|#########4| 161M/170M [00:03<00:00, 46.5MB/s]
- 98%|#########8| 166M/170M [00:03<00:00, 49.0MB/s]
-100%|##########| 170M/170M [00:03<00:00, 48.5MB/s]
+ 12%|#1 | 20.1M/170M [00:00<00:00, 211MB/s]
+ 28%|##7 | 47.3M/170M [00:00<00:00, 254MB/s]
+ 44%|####3 | 74.2M/170M [00:00<00:00, 267MB/s]
+ 60%|#####9 | 101M/170M [00:00<00:00, 273MB/s]
+ 75%|#######5 | 128M/170M [00:00<00:00, 276MB/s]
+ 91%|#########1| 155M/170M [00:00<00:00, 277MB/s]
+100%|##########| 170M/170M [00:00<00:00, 271MB/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').
@@ -539,7 +513,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.511 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 56.825 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 13351f37b..9a67f539a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,10 +450,9 @@ 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]
- 26%|##6 | 3.55M/13.6M [00:00<00:00, 37.2MB/s]
- 52%|#####2 | 7.11M/13.6M [00:00<00:00, 37.2MB/s]
- 91%|######### | 12.3M/13.6M [00:00<00:00, 45.1MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 44.6MB/s]
+ 36%|###5 | 4.88M/13.6M [00:00<00:00, 51.1MB/s]
+ 77%|#######7 | 10.4M/13.6M [00:00<00:00, 55.4MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 66.7MB/s]
</pre></div>
</div>
</div>
@@ -547,7 +546,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 88.2732 88.1940 88.8165 87.9212 0.2529
+ 90.1554 90.0577 91.3453 89.8888 0.2695
</pre></div>
</div>
<div class="admonition note">
@@ -586,7 +585,7 @@ 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 4.686 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.558 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 36e4ef6ba..5348e0147 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -545,7 +545,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<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)
- 118.3424 118.2984 122.6727 117.5725 0.5796
+ 117.2878 116.9891 122.3920 115.7325 1.0761
</pre></div>
</div>
<div class="admonition note">
@@ -573,7 +573,7 @@ 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 52.755 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.041 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 53435dde4..6f4de11bc 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -482,7 +482,7 @@ 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 51.853 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.950 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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 a94a5b2b6..61a8c5640 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,22 +415,23 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6424/132723 [00:00<00:01, 64233.32KB/s]
- 12%|#1 | 15284/132723 [00:00<00:01, 78561.36KB/s]
- 18%|#8 | 24246/132723 [00:00<00:01, 83605.71KB/s]
- 25%|##4 | 33136/132723 [00:00<00:01, 85692.82KB/s]
- 32%|###1 | 42050/132723 [00:00<00:01, 86933.23KB/s]
- 38%|###8 | 50902/132723 [00:00<00:00, 87468.26KB/s]
- 45%|####5 | 59770/132723 [00:00<00:00, 87861.67KB/s]
- 52%|#####1 | 68724/132723 [00:00<00:00, 88392.60KB/s]
- 59%|#####8 | 77674/132723 [00:00<00:00, 88737.60KB/s]
- 65%|######5 | 86614/132723 [00:01<00:00, 88940.47KB/s]
- 72%|#######1 | 95514/132723 [00:01<00:00, 88956.44KB/s]
- 79%|#######8 | 104410/132723 [00:01<00:00, 74968.58KB/s]
- 85%|########5 | 113305/132723 [00:01<00:00, 78713.04KB/s]
- 92%|#########1| 121483/132723 [00:01<00:00, 76630.75KB/s]
- 98%|#########8| 130361/132723 [00:01<00:00, 79978.41KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 82763.09KB/s]
+ 5%|5 | 6702/132723 [00:00<00:01, 67008.72KB/s]
+ 11%|#1 | 14782/132723 [00:00<00:01, 75117.77KB/s]
+ 17%|#7 | 22903/132723 [00:00<00:01, 77895.41KB/s]
+ 23%|##3 | 31126/132723 [00:00<00:01, 79602.38KB/s]
+ 30%|##9 | 39351/132723 [00:00<00:01, 80555.01KB/s]
+ 36%|###5 | 47561/132723 [00:00<00:01, 81075.50KB/s]
+ 42%|####2 | 55803/132723 [00:00<00:00, 81512.43KB/s]
+ 48%|####8 | 64005/132723 [00:00<00:00, 81670.99KB/s]
+ 54%|#####4 | 72233/132723 [00:00<00:00, 81859.37KB/s]
+ 61%|###### | 80452/132723 [00:01<00:00, 81960.38KB/s]
+ 67%|######6 | 88722/132723 [00:01<00:00, 82185.19KB/s]
+ 73%|#######3 | 96955/132723 [00:01<00:00, 82228.25KB/s]
+ 79%|#######9 | 105214/132723 [00:01<00:00, 82336.90KB/s]
+ 85%|########5 | 113448/132723 [00:01<00:00, 82294.84KB/s]
+ 92%|#########1| 121730/132723 [00:01<00:00, 82452.15KB/s]
+ 98%|#########7| 129978/132723 [00:01<00:00, 82459.20KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 81222.94KB/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
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.892 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 18.835 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 d47042f41..9e581fc5b 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>11:04.158</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:08.724</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:02.511</strong>: <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></li>
-<li><p><strong>02:22.892</strong>: <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></li>
-<li><p><strong>01:52.755</strong>: <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></li>
-<li><p><strong>01:51.853</strong>: <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></li>
-<li><p><strong>01:04.686</strong>: <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></li>
-<li><p><strong>00:28.016</strong>: <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></li>
-<li><p><strong>00:21.243</strong>: <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></li>
-<li><p><strong>00:00.202</strong>: <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></li>
+<li><p><strong>02:56.825</strong>: <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></li>
+<li><p><strong>02:18.835</strong>: <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></li>
+<li><p><strong>01:52.041</strong>: <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></li>
+<li><p><strong>01:08.950</strong>: <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></li>
+<li><p><strong>01:03.558</strong>: <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></li>
+<li><p><strong>00:27.239</strong>: <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></li>
+<li><p><strong>00:21.100</strong>: <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></li>
+<li><p><strong>00:00.176</strong>: <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></li>
</ul>
</div>
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 96708500b..f27cb5549 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -590,7 +590,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip9f51e92b-0a8d-4586-b71c-72ab496afebb 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.zipae495c75-b9a2-4265-a5ef-b569bcec0291 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>
@@ -652,7 +652,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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 registerd 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 bb659b3f5..0bf2cf631 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:37.579</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.747</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.159</strong>: <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></li>
-<li><p><strong>00:02.211</strong>: <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></li>
-<li><p><strong>00:01.007</strong>: <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></li>
-<li><p><strong>00:00.202</strong>: <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></li>
+<li><p><strong>00:35.230</strong>: <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></li>
+<li><p><strong>00:02.261</strong>: <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></li>
+<li><p><strong>00:01.053</strong>: <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></li>
+<li><p><strong>00:00.203</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 4d7382e93..00a626253 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5738us [5738us] (44.86%; 44.86%)
-FoldScaleAxis: 7052us [2us] (55.14%; 55.14%)
- FoldConstant: 7050us [1467us] (55.12%; 99.97%)
- InferType: 5583us [5583us] (43.65%; 79.20%)
+InferType: 6056us [6056us] (45.27%; 45.27%)
+FoldScaleAxis: 7323us [2us] (54.73%; 54.73%)
+ FoldConstant: 7321us [1568us] (54.72%; 99.97%)
+ InferType: 5753us [5753us] (43.00%; 78.59%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 5614us [5614us] (44.43%; 44.43%)
-FoldScaleAxis: 7020us [2us] (55.57%; 55.57%)
- FoldConstant: 7018us [1522us] (55.55%; 99.97%)
- InferType: 5497us [5497us] (43.51%; 78.32%)
+InferType: 5773us [5773us] (44.82%; 44.82%)
+FoldScaleAxis: 7108us [2us] (55.18%; 55.18%)
+ FoldConstant: 7107us [1473us] (55.17%; 99.98%)
+ InferType: 5634us [5634us] (43.74%; 79.28%)
</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 02accd7c9..84d54f200 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -538,7 +538,7 @@ latency of convolution.</p>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
-Convolution: 54.243287 ms
+Convolution: 54.219296 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 a1b979fcc..bd7c1bf2d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -882,7 +882,7 @@ be able to run on our build server</p>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
-conv2d with tensor core: 6.618245 ms
+conv2d with tensor core: 6.507978 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 796105f5f..c64fcdf3d 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,10 +431,10 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019255
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019207
/workspace/python/tvm/target/target.py:317: 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. "
-Baseline: 3.443456
+Baseline: 3.334489
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -496,7 +496,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.312268
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.307748
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -565,7 +565,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.344336
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332632
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -628,7 +628,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.122771
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118433
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -713,7 +713,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110611
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110538
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -801,7 +801,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111446
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111227
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -893,7 +893,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146447
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145653
</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 e712ce23c..f1b5fb389 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.704</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:35.014</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.956</strong>: <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></li>
-<li><p><strong>00:01.477</strong>: <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></li>
-<li><p><strong>00:01.271</strong>: <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></li>
+<li><p><strong>00:32.349</strong>: <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></li>
+<li><p><strong>00:01.445</strong>: <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></li>
+<li><p><strong>00:01.220</strong>: <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></li>
</ul>
</div>
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 d9d22048d..c67712d42 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>04:56.748</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:07.888</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:23.155</strong>: <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></li>
-<li><p><strong>01:18.088</strong>: <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></li>
-<li><p><strong>00:39.961</strong>: <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></li>
-<li><p><strong>00:18.067</strong>: <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></li>
-<li><p><strong>00:09.152</strong>: <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></li>
-<li><p><strong>00:08.325</strong>: <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></li>
+<li><p><strong>02:34.522</strong>: <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></li>
+<li><p><strong>01:18.267</strong>: <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></li>
+<li><p><strong>00:40.276</strong>: <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></li>
+<li><p><strong>00:17.457</strong>: <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></li>
+<li><p><strong>00:09.018</strong>: <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></li>
+<li><p><strong>00:08.349</strong>: <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></li>
</ul>
</div>
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 862ff8efa..994d792c0 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
@@ -470,469 +470,568 @@ 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" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [4]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [6144]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- 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, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
- for (rc.outer.outer: int32, 0, 8) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*3136)
- let cse_var_1: int32 = (rc.outer.outer*576)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], 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_2 + (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" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 56), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(t [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 6), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 6), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 168), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 1), 9)) && (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_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 280), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 2744)] = @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_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 392), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod( [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 3528)] = @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_2 + (floordiv(floordiv(threadIdx.x_1, 7), 9)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) + 2736)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormo [...]
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [6144], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 294), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 343), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 56), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 64), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 441), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 72), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 490), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 80), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 539), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 88), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 4704)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 588), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 96), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 5096)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 637), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 104), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 5488)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 686), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 112), 192)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 264), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 5880)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 735), 24)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 120), 192)*3)) + rx.outer.outer)]
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 33)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 34)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 35)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 36)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 37)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 38)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 39)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 40)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 41)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 42)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 43)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 44)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 45)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 46)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 47)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 48)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 49)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 50)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 51)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 52)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 53)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 54)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 55)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 56)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 57)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 58)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 59)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 60)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 61)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 62)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 63)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 64)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 65)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 66)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 67)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 68)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 69)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 70)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 71)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 72)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 73)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 74)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 75)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 76)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 77)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 78)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 79)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 80)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 81)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 82)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 83)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 84)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 85)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 86)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 87)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 88)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 89)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 90)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 91)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 92)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 93)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 94)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 193)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 194)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 196)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 197)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 199)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 200)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 202)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 203)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 205)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 206)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 208)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 209)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 210)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 211)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 212)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 213)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 214)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 215)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 216)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 217)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 218)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 219)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 220)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 221)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 222)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 223)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 224)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 225)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 226)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 227)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 228)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 229)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 230)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 231)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 232)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 233)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 234)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 235)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 236)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 237)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 238)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 239)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 240)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 241)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 242)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 243)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 244)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 245)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 246)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 247)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 248)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 249)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 250)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 251)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 252)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 253)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 254)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 255)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 256)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 257)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 258)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 259)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 260)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 261)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 262)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 263)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 264)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 265)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 266)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 267)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 268)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 269)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 270)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 271)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 272)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 273)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 274)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 275)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 276)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 277)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 278)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 279)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 280)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 281)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 282)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 283)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 284)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 285)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 286)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 287)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 384)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 385)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 386)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 387)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 388)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 389)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 390)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 391)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 392)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 393)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 394)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 395)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 396)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 397)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 398)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 399)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 400)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 401)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 402)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 403)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 404)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 405)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 406)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 407)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 408)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 409)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 410)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 411)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 412)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 413)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 414)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 415)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 416)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 417)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 418)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 419)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 420)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 421)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 422)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 423)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 424)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 425)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 426)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 427)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 428)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 429)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 430)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 431)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 432)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 433)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 434)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 435)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 436)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 437)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 438)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 439)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 440)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 441)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 442)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 443)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 444)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 445)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 446)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 447)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 448)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 449)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 450)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 451)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 452)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 453)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 454)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 455)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 456)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 457)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 458)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 459)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 460)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 461)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 462)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 463)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 464)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 465)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 466)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 467)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 468)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 469)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 470)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 471)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 472)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 473)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 474)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 475)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 476)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 477)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 478)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 479)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((rc.outer.inner*2016) + floormod(threadIdx.x, 49))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 576)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 577)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 578)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 579)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 70)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 580)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 77)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 581)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 582)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 133)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 583)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 140)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 584)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 585)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 586)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 203)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 587)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 588)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 259)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 589)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 266)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 590)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 591)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 322)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 592)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 329)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 593)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 378)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 594)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 385)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 595)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 392)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 596)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 441)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 597)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 598)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 455)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 599)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 600)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 601)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 518)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 602)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 603)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 574)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 604)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 581)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 605)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 630)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 606)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 637)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 607)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 644)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 608)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 693)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 700)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 610)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 707)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 611)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 756)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 763)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 613)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 770)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 614)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 826)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 616)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 833)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 617)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 882)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 889)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 619)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 896)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 620)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 945)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 952)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 622)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 959)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 623)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1008)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1015)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 625)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1022)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 626)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 627)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1078)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 628)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1085)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 629)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 630)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1141)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 631)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1148)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 632)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1197)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 633)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1204)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 634)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1211)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 635)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1260)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 636)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1267)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 637)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1274)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 638)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1323)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 639)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1330)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 640)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1337)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 641)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 642)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1393)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 643)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1400)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 644)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1449)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 645)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1456)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 646)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1463)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 647)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1512)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 648)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1519)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 649)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1526)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 650)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1575)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 651)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1582)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 652)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1589)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 653)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 654)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1645)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 655)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1652)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 656)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 657)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1708)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 658)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1715)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 659)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1764)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 660)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1771)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 661)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1778)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 662)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1827)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 663)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1834)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 664)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1841)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 665)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1890)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 666)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1897)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 667)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1904)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 668)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 669)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1960)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 670)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*2016) + floormod(threadIdx.x, 49)) + 1967)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*768) + (rc.outer.inner*96)) + 671)]))
- }
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 336), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 42), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
+ if @tir.likely((threadIdx.x_2 < 32), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 7))]), 0f32)
}
}
}
@@ -974,7 +1073,7 @@ cooperative fetching, unrolling and operator fusion.</p>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
-Execution time of this operator: 0.332 ms
+Execution time of this operator: 0.183 ms
</pre></div>
</div>
</div>
@@ -1005,32 +1104,32 @@ 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=8)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=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=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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)
@@ -1053,12 +1152,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
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=392)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -1080,439 +1179,548 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[4];
- __shared__ float pad_temp_shared[4032];
- __shared__ float kernel_shared[6144];
+extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[1152];
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 < 8; ++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 * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 392) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= (((((int)threadIdx.x) / 7) + 6) % 9)) && ((((((int)threadIdx.x) / 7) + 6) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1176) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 6) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= (((((int)threadIdx.x) / 7) + 1) % 9)) && ((((((int)threadIdx.x) / 7) + 1) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1960) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 1) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2744)] = (((((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 * 3136) + (((((int)threadIdx.x) + 2744) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 3528)] = (((((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 * 3136) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) + 2736)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 112) {
- pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 8) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 24) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 40) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 56) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3136) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 64) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3528) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 72) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 3920) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 80) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4312) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 88) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 4704)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 4704) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 96) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 5096)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5096) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 104) % 192) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 5488)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5488) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 112) % 192) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 264) {
- kernel_shared[(((int)threadIdx.x) + 5880)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 5880) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 120) % 192) * 3)) + rx_outer_outer)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[(((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 33)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 34)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 35)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 36)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 37)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 38)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 39)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 40)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 41)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 42)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 43)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 44)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 45)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 46)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 47)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 48)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 49)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 50)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 51)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 52)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 53)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 54)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 55)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 56)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 57)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 58)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 59)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 60)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 61)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 62)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 63)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 64)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 65)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 66)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 67)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 68)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 69)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 70)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 71)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 72)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 73)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 74)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 75)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 76)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 77)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 78)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 79)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 80)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 81)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 82)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 83)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 84)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 85)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 86)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 87)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 88)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 89)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 90)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 91)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 92)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 93)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 94)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 193)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 194)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 196)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 197)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 199)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 200)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 202)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 203)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 205)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 206)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 208)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 209)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 210)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 211)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 212)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 213)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 214)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 215)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 216)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 217)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 218)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 219)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 220)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 221)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 222)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 223)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 224)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 225)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 226)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 227)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 228)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 229)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 230)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 231)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 232)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 233)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 234)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 235)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 236)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 237)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 238)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 239)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 240)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 241)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 242)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 243)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 244)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 245)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 246)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 247)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 248)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 249)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 250)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 251)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 252)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 253)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 254)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 255)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 256)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 257)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 258)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 259)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 260)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 261)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 262)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 263)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 264)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 265)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 266)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 267)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 268)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 269)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 270)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 271)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 272)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 273)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 274)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 275)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 276)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 277)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 278)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 279)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 280)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 281)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 282)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 283)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 284)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 285)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 286)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 287)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 384)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 385)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 386)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 387)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 388)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 389)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 390)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 391)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 392)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 393)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 394)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 395)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 396)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 397)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 398)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 399)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 400)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 401)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 402)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 403)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 404)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 405)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 406)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 407)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 408)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 409)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 410)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 411)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 412)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 413)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 414)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 415)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 416)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 417)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 418)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 419)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 420)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 421)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 422)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 423)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 424)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 425)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 426)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 427)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 428)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 429)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 430)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 431)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 432)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 433)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 434)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 435)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 436)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 437)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 438)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 439)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 440)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 441)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 442)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 443)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 444)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 445)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 446)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 447)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 448)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 449)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 450)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 451)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 452)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 453)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 454)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 455)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 456)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 457)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 458)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 459)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 460)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 461)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 462)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 463)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 464)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 465)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 466)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 467)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 468)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 469)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 470)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 471)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 472)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 473)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 474)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 475)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 476)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 477)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 478)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 479)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49))] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 576)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 577)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 578)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 579)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 70)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 580)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 77)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 581)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 582)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 133)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 583)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 140)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 584)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 585)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 586)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 203)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 587)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 588)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 259)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 589)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 266)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 590)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 591)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 322)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 592)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 329)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 593)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 378)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 594)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 385)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 595)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 392)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 596)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 441)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 597)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 598)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 455)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 599)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 600)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 601)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 518)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 602)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 603)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 574)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 604)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 581)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 605)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 630)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 606)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 637)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 607)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 644)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 608)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 693)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 700)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 610)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 707)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 611)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 756)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 763)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 613)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 770)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 614)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 826)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 616)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 833)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 617)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 882)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 889)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 619)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 896)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 620)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 945)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 952)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 622)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 959)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 623)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1008)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1015)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 625)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1022)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 626)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 627)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1078)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 628)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1085)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 629)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 630)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1141)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 631)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1148)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 632)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1197)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 633)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1204)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 634)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1211)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 635)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1260)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 636)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1267)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 637)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1274)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 638)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1323)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 639)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1330)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 640)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1337)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 641)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 642)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1393)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 643)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1400)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 644)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1449)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 645)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1456)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 646)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1463)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 647)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1512)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 648)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1519)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 649)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1526)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 650)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1575)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 651)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1582)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 652)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1589)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 653)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 654)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1645)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 655)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1652)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 656)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 657)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1708)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 658)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1715)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 659)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1764)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 660)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1771)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 661)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1778)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 662)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1827)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 663)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1834)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 664)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1841)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 665)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1890)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 666)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1897)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 667)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1904)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 668)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 669)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1960)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 670)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 2016) + (((int)threadIdx.x) % 49)) + 1967)] * kernel_shared[((((((int)threadIdx.x) / 49) * 768) + (rc_outer_inner * 96)) + 671)]));
- }
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 88) {
+ pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 40) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 64512)];
+ if (((int)threadIdx.x) < 32) {
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
}
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
}
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
}
}
</pre></div>
@@ -1550,7 +1758,7 @@ 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 23.155 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 34.522 seconds)</p>
<div class="sphx-glr-footer class 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 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 cc99e7292..2ad5d4a9d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -878,7 +878,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7129 9.7105 9.7590 9.6691 0.0367
+ 9.7495 9.7583 9.7772 9.7130 0.0270
</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 f98c9d431..a7129aab8 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -897,7 +897,7 @@ 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)
- 736.0303 737.0998 741.1594 729.8317 4.6859
+ 761.6180 761.5995 761.8257 761.4287 0.1626
</pre></div>
</div>
</div>
@@ -919,7 +919,7 @@ 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 18.088 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.267 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 505762040..9f5a42c45 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,409 +600,76 @@ 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_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32)
- let cse_var_1: int32 = (i.outer.inner*128)
- {
- compute_5: Buffer(compute_4, float32, [512], [])[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
- compute_5[(cse_var_1 + 16)] = 0f32
- compute_5[(cse_var_1 + 17)] = 0f32
- compute_5[(cse_var_1 + 18)] = 0f32
- compute_5[(cse_var_1 + 19)] = 0f32
- compute_5[(cse_var_1 + 20)] = 0f32
- compute_5[(cse_var_1 + 21)] = 0f32
- compute_5[(cse_var_1 + 22)] = 0f32
- compute_5[(cse_var_1 + 23)] = 0f32
- compute_5[(cse_var_1 + 24)] = 0f32
- compute_5[(cse_var_1 + 25)] = 0f32
- compute_5[(cse_var_1 + 26)] = 0f32
- compute_5[(cse_var_1 + 27)] = 0f32
- compute_5[(cse_var_1 + 28)] = 0f32
- compute_5[(cse_var_1 + 29)] = 0f32
- compute_5[(cse_var_1 + 30)] = 0f32
- compute_5[(cse_var_1 + 31)] = 0f32
- compute_5[(cse_var_1 + 32)] = 0f32
- compute_5[(cse_var_1 + 33)] = 0f32
- compute_5[(cse_var_1 + 34)] = 0f32
- compute_5[(cse_var_1 + 35)] = 0f32
- compute_5[(cse_var_1 + 36)] = 0f32
- compute_5[(cse_var_1 + 37)] = 0f32
- compute_5[(cse_var_1 + 38)] = 0f32
- compute_5[(cse_var_1 + 39)] = 0f32
- compute_5[(cse_var_1 + 40)] = 0f32
- compute_5[(cse_var_1 + 41)] = 0f32
- compute_5[(cse_var_1 + 42)] = 0f32
- compute_5[(cse_var_1 + 43)] = 0f32
- compute_5[(cse_var_1 + 44)] = 0f32
- compute_5[(cse_var_1 + 45)] = 0f32
- compute_5[(cse_var_1 + 46)] = 0f32
- compute_5[(cse_var_1 + 47)] = 0f32
- compute_5[(cse_var_1 + 48)] = 0f32
- compute_5[(cse_var_1 + 49)] = 0f32
- compute_5[(cse_var_1 + 50)] = 0f32
- compute_5[(cse_var_1 + 51)] = 0f32
- compute_5[(cse_var_1 + 52)] = 0f32
- compute_5[(cse_var_1 + 53)] = 0f32
- compute_5[(cse_var_1 + 54)] = 0f32
- compute_5[(cse_var_1 + 55)] = 0f32
- compute_5[(cse_var_1 + 56)] = 0f32
- compute_5[(cse_var_1 + 57)] = 0f32
- compute_5[(cse_var_1 + 58)] = 0f32
- compute_5[(cse_var_1 + 59)] = 0f32
- compute_5[(cse_var_1 + 60)] = 0f32
- compute_5[(cse_var_1 + 61)] = 0f32
- compute_5[(cse_var_1 + 62)] = 0f32
- compute_5[(cse_var_1 + 63)] = 0f32
- compute_5[(cse_var_1 + 64)] = 0f32
- compute_5[(cse_var_1 + 65)] = 0f32
- compute_5[(cse_var_1 + 66)] = 0f32
- compute_5[(cse_var_1 + 67)] = 0f32
- compute_5[(cse_var_1 + 68)] = 0f32
- compute_5[(cse_var_1 + 69)] = 0f32
- compute_5[(cse_var_1 + 70)] = 0f32
- compute_5[(cse_var_1 + 71)] = 0f32
- compute_5[(cse_var_1 + 72)] = 0f32
- compute_5[(cse_var_1 + 73)] = 0f32
- compute_5[(cse_var_1 + 74)] = 0f32
- compute_5[(cse_var_1 + 75)] = 0f32
- compute_5[(cse_var_1 + 76)] = 0f32
- compute_5[(cse_var_1 + 77)] = 0f32
- compute_5[(cse_var_1 + 78)] = 0f32
- compute_5[(cse_var_1 + 79)] = 0f32
- compute_5[(cse_var_1 + 80)] = 0f32
- compute_5[(cse_var_1 + 81)] = 0f32
- compute_5[(cse_var_1 + 82)] = 0f32
- compute_5[(cse_var_1 + 83)] = 0f32
- compute_5[(cse_var_1 + 84)] = 0f32
- compute_5[(cse_var_1 + 85)] = 0f32
- compute_5[(cse_var_1 + 86)] = 0f32
- compute_5[(cse_var_1 + 87)] = 0f32
- compute_5[(cse_var_1 + 88)] = 0f32
- compute_5[(cse_var_1 + 89)] = 0f32
- compute_5[(cse_var_1 + 90)] = 0f32
- compute_5[(cse_var_1 + 91)] = 0f32
- compute_5[(cse_var_1 + 92)] = 0f32
- compute_5[(cse_var_1 + 93)] = 0f32
- compute_5[(cse_var_1 + 94)] = 0f32
- compute_5[(cse_var_1 + 95)] = 0f32
- compute_5[(cse_var_1 + 96)] = 0f32
- compute_5[(cse_var_1 + 97)] = 0f32
- compute_5[(cse_var_1 + 98)] = 0f32
- compute_5[(cse_var_1 + 99)] = 0f32
- compute_5[(cse_var_1 + 100)] = 0f32
- compute_5[(cse_var_1 + 101)] = 0f32
- compute_5[(cse_var_1 + 102)] = 0f32
- compute_5[(cse_var_1 + 103)] = 0f32
- compute_5[(cse_var_1 + 104)] = 0f32
- compute_5[(cse_var_1 + 105)] = 0f32
- compute_5[(cse_var_1 + 106)] = 0f32
- compute_5[(cse_var_1 + 107)] = 0f32
- compute_5[(cse_var_1 + 108)] = 0f32
- compute_5[(cse_var_1 + 109)] = 0f32
- compute_5[(cse_var_1 + 110)] = 0f32
- compute_5[(cse_var_1 + 111)] = 0f32
- compute_5[(cse_var_1 + 112)] = 0f32
- compute_5[(cse_var_1 + 113)] = 0f32
- compute_5[(cse_var_1 + 114)] = 0f32
- compute_5[(cse_var_1 + 115)] = 0f32
- compute_5[(cse_var_1 + 116)] = 0f32
- compute_5[(cse_var_1 + 117)] = 0f32
- compute_5[(cse_var_1 + 118)] = 0f32
- compute_5[(cse_var_1 + 119)] = 0f32
- compute_5[(cse_var_1 + 120)] = 0f32
- compute_5[(cse_var_1 + 121)] = 0f32
- compute_5[(cse_var_1 + 122)] = 0f32
- compute_5[(cse_var_1 + 123)] = 0f32
- compute_5[(cse_var_1 + 124)] = 0f32
- compute_5[(cse_var_1 + 125)] = 0f32
- compute_5[(cse_var_1 + 126)] = 0f32
- compute_5[(cse_var_1 + 127)] = 0f32
- for (elem_idx: int32, 0, (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- let cse_var_131: int32 = (cse_var_1 + 13)
- let cse_var_130: int32 = (cse_var_1 + 14)
- let cse_var_129: int32 = (cse_var_1 + 15)
- let cse_var_128: int32 = (cse_var_1 + 16)
- let cse_var_127: int32 = (cse_var_1 + 17)
- let cse_var_126: int32 = (cse_var_1 + 18)
- let cse_var_125: int32 = (cse_var_1 + 19)
- let cse_var_124: int32 = (cse_var_1 + 2)
- let cse_var_123: int32 = (cse_var_1 + 20)
- let cse_var_122: int32 = (cse_var_1 + 21)
- let cse_var_121: int32 = (cse_var_1 + 22)
- let cse_var_120: int32 = (cse_var_1 + 23)
- let cse_var_119: int32 = (cse_var_1 + 24)
- let cse_var_118: int32 = (cse_var_1 + 25)
- let cse_var_117: int32 = (cse_var_1 + 26)
- let cse_var_116: int32 = (cse_var_1 + 42)
- let cse_var_115: int32 = (cse_var_1 + 28)
- let cse_var_114: int32 = (cse_var_1 + 29)
- let cse_var_113: int32 = (cse_var_1 + 3)
- let cse_var_112: int32 = (cse_var_1 + 30)
- let cse_var_111: int32 = (cse_var_1 + 31)
- let cse_var_110: int32 = (cse_var_1 + 32)
- let cse_var_109: int32 = (cse_var_1 + 33)
- let cse_var_108: int32 = (cse_var_1 + 34)
- let cse_var_107: int32 = (cse_var_1 + 35)
- let cse_var_106: int32 = (cse_var_1 + 36)
- let cse_var_105: int32 = (cse_var_1 + 37)
- let cse_var_104: int32 = (cse_var_1 + 38)
- let cse_var_103: int32 = (cse_var_1 + 39)
- let cse_var_102: int32 = (cse_var_1 + 4)
- let cse_var_101: int32 = (cse_var_1 + 40)
- let cse_var_100: int32 = (cse_var_1 + 27)
- let cse_var_99: int32 = (cse_var_1 + 1)
- let cse_var_98: int32 = (cse_var_1 + 10)
- let cse_var_97: int32 = (cse_var_1 + 100)
- let cse_var_96: int32 = (cse_var_1 + 101)
- let cse_var_95: int32 = (cse_var_1 + 102)
- let cse_var_94: int32 = (cse_var_1 + 103)
- let cse_var_93: int32 = (cse_var_1 + 104)
- let cse_var_92: int32 = (cse_var_1 + 105)
- let cse_var_91: int32 = (cse_var_1 + 106)
- let cse_var_90: int32 = (cse_var_1 + 107)
- let cse_var_89: int32 = (cse_var_1 + 108)
- let cse_var_88: int32 = (cse_var_1 + 109)
- let cse_var_87: int32 = (cse_var_1 + 11)
- let cse_var_86: int32 = (cse_var_1 + 110)
- let cse_var_85: int32 = (cse_var_1 + 111)
- let cse_var_84: int32 = (cse_var_1 + 127)
- let cse_var_83: int32 = (cse_var_1 + 113)
- let cse_var_82: int32 = (cse_var_1 + 114)
- let cse_var_81: int32 = (cse_var_1 + 115)
- let cse_var_80: int32 = (cse_var_1 + 116)
- let cse_var_79: int32 = (cse_var_1 + 117)
- let cse_var_78: int32 = (cse_var_1 + 118)
- let cse_var_77: int32 = (cse_var_1 + 119)
- let cse_var_76: int32 = (cse_var_1 + 12)
- let cse_var_75: int32 = (cse_var_1 + 120)
- let cse_var_74: int32 = (cse_var_1 + 121)
- let cse_var_73: int32 = (cse_var_1 + 122)
- let cse_var_72: int32 = (cse_var_1 + 123)
- let cse_var_71: int32 = (cse_var_1 + 124)
- let cse_var_70: int32 = (cse_var_1 + 125)
- let cse_var_69: int32 = (cse_var_1 + 126)
- let cse_var_68: int32 = (cse_var_1 + 112)
- let cse_var_67: int32 = (cse_var_1 + 72)
- let cse_var_66: int32 = (cse_var_1 + 73)
- let cse_var_65: int32 = (cse_var_1 + 74)
- let cse_var_64: int32 = (cse_var_1 + 75)
- let cse_var_63: int32 = (cse_var_1 + 76)
- let cse_var_62: int32 = (cse_var_1 + 77)
- let cse_var_61: int32 = (cse_var_1 + 78)
- let cse_var_60: int32 = (cse_var_1 + 79)
- let cse_var_59: int32 = (cse_var_1 + 8)
- let cse_var_58: int32 = (cse_var_1 + 80)
- let cse_var_57: int32 = (cse_var_1 + 81)
- let cse_var_56: int32 = (cse_var_1 + 82)
- let cse_var_55: int32 = (cse_var_1 + 83)
- let cse_var_54: int32 = (cse_var_1 + 84)
- let cse_var_53: int32 = (cse_var_1 + 85)
- let cse_var_52: int32 = (cse_var_1 + 41)
- let cse_var_51: int32 = (cse_var_1 + 87)
- let cse_var_50: int32 = (cse_var_1 + 88)
- let cse_var_49: int32 = (cse_var_1 + 89)
- let cse_var_48: int32 = (cse_var_1 + 9)
- let cse_var_47: int32 = (cse_var_1 + 90)
- let cse_var_46: int32 = (cse_var_1 + 91)
- let cse_var_45: int32 = (cse_var_1 + 92)
- let cse_var_44: int32 = (cse_var_1 + 93)
- let cse_var_43: int32 = (cse_var_1 + 94)
- let cse_var_42: int32 = (cse_var_1 + 95)
- let cse_var_41: int32 = (cse_var_1 + 96)
- let cse_var_40: int32 = (cse_var_1 + 97)
- let cse_var_39: int32 = (cse_var_1 + 98)
- let cse_var_38: int32 = (cse_var_1 + 99)
- let cse_var_37: int32 = (elem_idx*16)
- let cse_var_36: int32 = (cse_var_1 + 86)
- let cse_var_35: int32 = (cse_var_1 + 43)
- let cse_var_34: int32 = (cse_var_1 + 44)
- let cse_var_33: int32 = (cse_var_1 + 45)
- let cse_var_32: int32 = (cse_var_1 + 46)
- let cse_var_31: int32 = (cse_var_1 + 47)
- let cse_var_30: int32 = (cse_var_1 + 48)
- let cse_var_29: int32 = (cse_var_1 + 49)
- let cse_var_28: int32 = (cse_var_1 + 5)
- let cse_var_27: int32 = (cse_var_1 + 50)
- let cse_var_26: int32 = (cse_var_1 + 51)
- let cse_var_25: int32 = (cse_var_1 + 52)
- let cse_var_24: int32 = (cse_var_1 + 53)
- let cse_var_23: int32 = (cse_var_1 + 54)
- let cse_var_22: int32 = (cse_var_1 + 55)
- let cse_var_21: int32 = (cse_var_1 + 56)
- let cse_var_20: int32 = (cse_var_1 + 57)
- let cse_var_19: int32 = (cse_var_1 + 71)
- let cse_var_18: int32 = (cse_var_1 + 7)
- let cse_var_17: int32 = (cse_var_1 + 69)
- let cse_var_16: int32 = (cse_var_1 + 68)
- let cse_var_15: int32 = (cse_var_1 + 67)
- let cse_var_14: int32 = (cse_var_1 + 66)
- let cse_var_13: int32 = (cse_var_1 + 65)
- let cse_var_12: int32 = (cse_var_1 + 64)
- let cse_var_11: int32 = (cse_var_1 + 63)
- let cse_var_10: int32 = (cse_var_1 + 62)
- let cse_var_9: int32 = (cse_var_1 + 61)
- let cse_var_8: int32 = (cse_var_1 + 60)
- let cse_var_7: int32 = (cse_var_1 + 6)
- let cse_var_6: int32 = (cse_var_1 + 59)
- let cse_var_5: int32 = (cse_var_1 + 70)
- let cse_var_4: int32 = (cse_var_1 + 58)
- let cse_var_3: int32 = ((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*2048))
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_19: Buffer(placeholder_10, float32, [128, 256], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 8) {
+ let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ {
+ compute_5: Buffer(compute_4, float32, [256], [])[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, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*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 = ((i.inner*32) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_18: int32 = (cse_var_20 + 1)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_20 + 10)
{
- compute_5[cse_var_1] = (compute_5[cse_var_1] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_99] = (compute_5[cse_var_99] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_124] = (compute_5[cse_var_124] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_113] = (compute_5[cse_var_113] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_102] = (compute_5[cse_var_102] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_59] = (compute_5[cse_var_59] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_48] = (compute_5[cse_var_48] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_98] = (compute_5[cse_var_98] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_87] = (compute_5[cse_var_87] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_76] = (compute_5[cse_var_76] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_131] = (compute_5[cse_var_131] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_130] = (compute_5[cse_var_130] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_129] = (compute_5[cse_var_129] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)])], 0f32)))
- compute_5[cse_var_128] = (compute_5[cse_var_128] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_127] = (compute_5[cse_var_127] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_126] = (compute_5[cse_var_126] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_125] = (compute_5[cse_var_125] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_123] = (compute_5[cse_var_123] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_122] = (compute_5[cse_var_122] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_121] = (compute_5[cse_var_121] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_120] = (compute_5[cse_var_120] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_119] = (compute_5[cse_var_119] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_118] = (compute_5[cse_var_118] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_117] = (compute_5[cse_var_117] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_100] = (compute_5[cse_var_100] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_115] = (compute_5[cse_var_115] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_114] = (compute_5[cse_var_114] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_112] = (compute_5[cse_var_112] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_111] = (compute_5[cse_var_111] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 256)], 0f32)))
- compute_5[cse_var_110] = (compute_5[cse_var_110] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_109] = (compute_5[cse_var_109] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_108] = (compute_5[cse_var_108] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_107] = (compute_5[cse_var_107] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_106] = (compute_5[cse_var_106] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_105] = (compute_5[cse_var_105] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_104] = (compute_5[cse_var_104] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_103] = (compute_5[cse_var_103] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_101] = (compute_5[cse_var_101] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_52] = (compute_5[cse_var_52] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_116] = (compute_5[cse_var_116] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 512)], 0f32)))
- compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 768)], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_67] = (compute_5[cse_var_67] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_66] = (compute_5[cse_var_66] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_65] = (compute_5[cse_var_65] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_64] = (compute_5[cse_var_64] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_63] = (compute_5[cse_var_63] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_62] = (compute_5[cse_var_62] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_61] = (compute_5[cse_var_61] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_60] = (compute_5[cse_var_60] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1024)], 0f32)))
- compute_5[cse_var_58] = (compute_5[cse_var_58] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_57] = (compute_5[cse_var_57] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_56] = (compute_5[cse_var_56] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_55] = (compute_5[cse_var_55] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_54] = (compute_5[cse_var_54] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_53] = (compute_5[cse_var_53] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_36] = (compute_5[cse_var_36] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_51] = (compute_5[cse_var_51] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_50] = (compute_5[cse_var_50] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_49] = (compute_5[cse_var_49] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_47] = (compute_5[cse_var_47] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_46] = (compute_5[cse_var_46] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_45] = (compute_5[cse_var_45] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_44] = (compute_5[cse_var_44] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_43] = (compute_5[cse_var_43] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_42] = (compute_5[cse_var_42] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1280)], 0f32)))
- compute_5[cse_var_41] = (compute_5[cse_var_41] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_40] = (compute_5[cse_var_40] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_39] = (compute_5[cse_var_39] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_38] = (compute_5[cse_var_38] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_97] = (compute_5[cse_var_97] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_96] = (compute_5[cse_var_96] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_95] = (compute_5[cse_var_95] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_94] = (compute_5[cse_var_94] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_93] = (compute_5[cse_var_93] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_92] = (compute_5[cse_var_92] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_91] = (compute_5[cse_var_91] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_90] = (compute_5[cse_var_90] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_89] = (compute_5[cse_var_89] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_88] = (compute_5[cse_var_88] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_86] = (compute_5[cse_var_86] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_85] = (compute_5[cse_var_85] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1536)], 0f32)))
- compute_5[cse_var_68] = (compute_5[cse_var_68] + (placeholder_1[((placeholder_3[cse_var_2]*16) + cse_var_37)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_83] = (compute_5[cse_var_83] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_82] = (compute_5[cse_var_82] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_81] = (compute_5[cse_var_81] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_80] = (compute_5[cse_var_80] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_79] = (compute_5[cse_var_79] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_78] = (compute_5[cse_var_78] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_77] = (compute_5[cse_var_77] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_75] = (compute_5[cse_var_75] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_74] = (compute_5[cse_var_74] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_73] = (compute_5[cse_var_73] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_72] = (compute_5[cse_var_72] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_71] = (compute_5[cse_var_71] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_70] = (compute_5[cse_var_70] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_69] = (compute_5[cse_var_69] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
- compute_5[cse_var_84] = (compute_5[cse_var_84] + (placeholder_1[(((placeholder_3[cse_var_2]*16) + cse_var_37) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_2] + elem_idx)]) + 1792)], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_132: int32 = ((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16)) + i1.inner)
- compute[cse_var_132] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_132]), 0f32)
- }
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -1043,7 +710,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/target/target.py:317: 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. "
-Execution time of this operator: 2.502 ms
+Execution time of this operator: 1.882 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 fc33b6abc..8bf7e42b8 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:44.935</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.936</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.053</strong>: <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></li>
-<li><p><strong>00:00.232</strong>: <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></li>
-<li><p><strong>00:00.218</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.216</strong>: <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></li>
-<li><p><strong>00:00.216</strong>: <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></li>
+<li><p><strong>00:44.096</strong>: <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></li>
+<li><p><strong>00:00.219</strong>: <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></li>
+<li><p><strong>00:00.211</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.207</strong>: <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></li>
+<li><p><strong>00:00.203</strong>: <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></li>
</ul>
</div>
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 7604579ac..b5933a20c 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.41/42.41 result: MeasureResult(costs=(0.0054580131578947375,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.575484037399292, timestamp=1653605049.7827628) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 6 GFLOPS: 93.78/93.78 result: MeasureResult(costs=(0.0024686733541666663,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.754946231842041, timestamp=1653652905.6925685) [('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: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/93.78 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
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.41 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/93.78 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f6b8eee2fa2
+ 12: 0x00007f9a19cb4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.76/143.76 result: MeasureResult(costs=(0.00161030436,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3760154247283936, timestamp=1653605076.1585646) [('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: 143.73/143.73 result: MeasureResult(costs=(0.0016106633299999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4333069324493408, timestamp=1653652932.1503072) [('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,
@@ -2710,7 +2710,7 @@ and measure running time.</p>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/target/target.py:317: 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. "
-Time cost of this operator: 0.001955
+Time cost of this operator: 0.002051
</pre></div>
</div>
<div class="sphx-glr-footer class 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 ff0838af5..a4a8dd3df 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -555,10 +555,10 @@ 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 312.0 98.728 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.953 0.934 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.067 0.338 (1, 1, 10, 10, 3) 1 1
-Total_time - 316.02 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.5 98.732 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.142 0.983 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.91 0.285 (1, 1, 10, 10, 3) 1 1
+Total_time - 319.552 - - - -
</pre></div>
</div>
</div>
@@ -610,10 +610,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 96.65 97.409 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.758 1.772 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.813 0.819 (1, 3, 10, 10, 1) 1 1
-Total_time - 99.221 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 225.5 98.746 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.047 0.896 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.816 0.357 (1, 3, 10, 10, 1) 1 1
+Total_time - 228.363 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index d53c6aed6..39bd7dff6 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:45.882</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:45.898</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:41.651</strong>: <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></li>
-<li><p><strong>00:03.632</strong>: <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></li>
-<li><p><strong>00:00.201</strong>: <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></li>
-<li><p><strong>00:00.200</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.199</strong>: <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></li>
+<li><p><strong>00:41.715</strong>: <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></li>
+<li><p><strong>00:03.604</strong>: <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></li>
+<li><p><strong>00:00.197</strong>: <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></li>
+<li><p><strong>00:00.193</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:00.190</strong>: <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></li>
</ul>
</div>
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 93653088a..309aa941c 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:12.157</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:12.310</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:09.980</strong>: <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></li>
-<li><p><strong>00:01.959</strong>: <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></li>
-<li><p><strong>00:00.219</strong>: <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></li>
+<li><p><strong>00:10.093</strong>: <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></li>
+<li><p><strong>00:02.012</strong>: <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></li>
+<li><p><strong>00:00.205</strong>: <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></li>
</ul>
</div>
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 343d43302..acc5a2b89 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:05.732</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.687</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.102</strong>: <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></li>
-<li><p><strong>00:01.142</strong>: <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></li>
-<li><p><strong>00:00.737</strong>: <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></li>
-<li><p><strong>00:00.727</strong>: <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></li>
-<li><p><strong>00:00.315</strong>: <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></li>
-<li><p><strong>00:00.243</strong>: <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></li>
-<li><p><strong>00:00.241</strong>: <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></li>
-<li><p><strong>00:00.225</strong>: <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></li>
+<li><p><strong>00:02.072</strong>: <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></li>
+<li><p><strong>00:01.203</strong>: <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></li>
+<li><p><strong>00:00.721</strong>: <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></li>
+<li><p><strong>00:00.703</strong>: <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></li>
+<li><p><strong>00:00.306</strong>: <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></li>
+<li><p><strong>00:00.243</strong>: <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></li>
+<li><p><strong>00:00.220</strong>: <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></li>
+<li><p><strong>00:00.219</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c631e18fd..56620b39a 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/tmplfm8mwyy/input0.cc'\nsource_filename = \"/tmp/tmplfm8mwyy/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/tmp4h4jocck/input0.cc'\nsource_filename = \"/tmp/tmp4h4jocck/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/doxygen/functions_d.html b/docs/reference/api/doxygen/functions_d.html
index ad32b6435..c1b9681d5 100644
--- a/docs/reference/api/doxygen/functions_d.html
+++ b/docs/reference/api/doxygen/functions_d.html
@@ -94,7 +94,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a44339b9feda8c50da6518cd7d66d9727">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a15350be67dd9492f29b828660a3f7a5f">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a6c5cbc7b988195cedade4c21dd5c0cd5">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5202a8aa859efcecab500f73304589fa">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a1263b2f122ed56faa812c76ecc115870">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#a2c9e71150087c06790b0f9c785e786c8">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#afbf41d75b87a6d33a15b4a9a9523710d">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71">tvm::relay::Dilation2DAttrs</a>
diff --git a/docs/reference/api/doxygen/functions_k.html b/docs/reference/api/doxygen/functions_k.html
index b8b8eab03..befce355c 100644
--- a/docs/reference/api/doxygen/functions_k.html
+++ b/docs/reference/api/doxygen/functions_k.html
@@ -98,7 +98,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#ad0839f3b82465c887a7da60c36b1bff0">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a132de48db6ed57c112774e1c0b5bbc4b">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a4727879df243b2e7e01efd13d9f90b70">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a4c7843b55a08d35ac511ff2bcabe3b00">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a7a3159f55dd2eaf15361d92f573fa19f">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#a3d3bde5aefe65c34791f60edc1744df0">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#a8c741a4815d5bb4a6573dd0b9edc3143">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53">tvm::relay::Dilation2DAttrs</a>
diff --git a/docs/reference/api/doxygen/functions_o.html b/docs/reference/api/doxygen/functions_o.html
index 66be4d230..e85237a1c 100644
--- a/docs/reference/api/doxygen/functions_o.html
+++ b/docs/reference/api/doxygen/functions_o.html
@@ -508,7 +508,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a51c1ecd25ffa7030b204acea2f029d09">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a96a9fb507c88d5982ea434b64dd06039">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#ac0c55c6ed61b2a425f5cfaa191f3470e">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#af749b3f0584da69970356728f42b9e6d">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#a5fd67780be31bad0d4d1c376967817e2">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1GlobalPool2DAttrs.html#af74536e73724dd74d7b5784c54b779cc">tvm::relay::GlobalPool2DAttrs</a>
diff --git a/docs/reference/api/doxygen/functions_vars_d.html b/docs/reference/api/doxygen/functions_vars_d.html
index e457b967f..dc9d85e8e 100644
--- a/docs/reference/api/doxygen/functions_vars_d.html
+++ b/docs/reference/api/doxygen/functions_vars_d.html
@@ -90,7 +90,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a44339b9feda8c50da6518cd7d66d9727">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a15350be67dd9492f29b828660a3f7a5f">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a6c5cbc7b988195cedade4c21dd5c0cd5">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5202a8aa859efcecab500f73304589fa">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a1263b2f122ed56faa812c76ecc115870">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#a2c9e71150087c06790b0f9c785e786c8">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#afbf41d75b87a6d33a15b4a9a9523710d">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71">tvm::relay::Dilation2DAttrs</a>
diff --git a/docs/reference/api/doxygen/functions_vars_k.html b/docs/reference/api/doxygen/functions_vars_k.html
index c088d9564..02ad4e315 100644
--- a/docs/reference/api/doxygen/functions_vars_k.html
+++ b/docs/reference/api/doxygen/functions_vars_k.html
@@ -86,7 +86,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#ad0839f3b82465c887a7da60c36b1bff0">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a132de48db6ed57c112774e1c0b5bbc4b">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a4727879df243b2e7e01efd13d9f90b70">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a4c7843b55a08d35ac511ff2bcabe3b00">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a7a3159f55dd2eaf15361d92f573fa19f">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#a3d3bde5aefe65c34791f60edc1744df0">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#a8c741a4815d5bb4a6573dd0b9edc3143">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53">tvm::relay::Dilation2DAttrs</a>
diff --git a/docs/reference/api/doxygen/functions_vars_o.html b/docs/reference/api/doxygen/functions_vars_o.html
index a53be7ad3..0cc041e05 100644
--- a/docs/reference/api/doxygen/functions_vars_o.html
+++ b/docs/reference/api/doxygen/functions_vars_o.html
@@ -159,7 +159,7 @@ $(function() {
, <a class="el" href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a51c1ecd25ffa7030b204acea2f029d09">tvm::relay::Conv2DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4">tvm::relay::Conv2DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6">tvm::relay::Conv3DAttrs</a>
-, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a96a9fb507c88d5982ea434b64dd06039">tvm::relay::Conv3DTransposeAttrs</a>
+, <a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#ac0c55c6ed61b2a425f5cfaa191f3470e">tvm::relay::Conv3DTransposeAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#af749b3f0584da69970356728f42b9e6d">tvm::relay::Conv3DWinogradAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#a5fd67780be31bad0d4d1c376967817e2">tvm::relay::DeformableConv2DAttrs</a>
, <a class="el" href="structtvm_1_1relay_1_1GlobalPool2DAttrs.html#af74536e73724dd74d7b5784c54b779cc">tvm::relay::GlobalPool2DAttrs</a>
diff --git a/docs/reference/api/doxygen/relay_2attrs_2nn_8h_source.html b/docs/reference/api/doxygen/relay_2attrs_2nn_8h_source.html
index cf7b888d3..4961407a8 100644
--- a/docs/reference/api/doxygen/relay_2attrs_2nn_8h_source.html
+++ b/docs/reference/api/doxygen/relay_2attrs_2nn_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">nn.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="relay_2attrs_2nn_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
+<a href="relay_2attrs_2nn_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DAttrs_html_aed6a9346217ee4817b028734c660cfb0"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DAttrs.html#aed6a9346217ee4817b028734c660cfb0">tvm::relay::Conv3DAttrs::dilation</a></div><div class="ttdeci">Array< IndexExpr > dilation</div><div class="ttdef"><b>Definition:</b> nn.h:304</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1UpSampling3DAttrs_html_af8891c263011a72ee4989a601b860f08"><div class="ttname"><a href="structtvm_1_1relay_1_1UpSampling3DAttrs.html#af8891c263011a72ee4989a601b860f08">tvm::relay::UpSampling3DAttrs::layout</a></div><div class="ttdeci">std::string layout</div><div class="ttdef"><b>Definition:</b> nn.h:1209</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1MaxPool2DAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1MaxPool2DAttrs.html">tvm::relay::MaxPool2DAttrs</a></div><div class="ttdoc">Attributes for max pool operator. </div><div class="ttdef"><b>Definition:</b> nn.h:689</div></div>
@@ -120,7 +120,6 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1LRNAttrs_html_ae6ffa2a5733be8a6fd1700ba5b00e12e"><div class="ttname"><a href="structtvm_1_1relay_1_1LRNAttrs.html#ae6ffa2a5733be8a6fd1700ba5b00e12e">tvm::relay::LRNAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(LRNAttrs, "relay.attrs.LRNAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:1395</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1AdaptivePool3DAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1AdaptivePool3DAttrs.html">tvm::relay::AdaptivePool3DAttrs</a></div><div class="ttdoc">Attributes for 3d adaptive pool operator. </div><div class="ttdef"><b>Definition:</b> nn.h:848</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_aafd4b90da8ce3dae0252be77b904414f"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#aafd4b90da8ce3dae0252be77b904414f">tvm::relay::Conv3DTransposeAttrs::channels</a></div><div class="ttdeci">IndexExpr channels</div><div class="ttdef"><b>Definition:</b> nn.h:373</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_a5202a8aa859efcecab500f73304589fa"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5202a8aa859efcecab500f73304589fa">tvm::relay::Conv3DTransposeAttrs::data_layout</a></div><div class="ttdeci">std::string data_layout</div><div class="ttdef"><b>Definition:</b> nn.h:380</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1AvgPool2DAttrs_html_a3290e2f8710e5d093a67896481895956"><div class="ttname"><a href="structtvm_1_1relay_1_1AvgPool2DAttrs.html#a3290e2f8710e5d093a67896481895956">tvm::relay::AvgPool2DAttrs::layout</a></div><div class="ttdeci">tvm::String layout</div><div class="ttdef"><b>Definition:</b> nn.h:737</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SpaceToBatchNDAttrs_html_aabc579d65229d49279a1c3a903a99095"><div class="ttname"><a href="structtvm_1_1relay_1_1SpaceToBatchNDAttrs.html#aabc579d65229d49279a1c3a903a99095">tvm::relay::SpaceToBatchNDAttrs::paddings</a></div><div class="ttdeci">Array< Array< IndexExpr > > paddings</div><div class="ttdef"><b>Definition:</b> nn.h:1545</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DWinogradAttrs_html_a6300f8aa97d520ad4a79d1071d821ec4"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4">tvm::relay::Conv2DWinogradAttrs::out_layout</a></div><div class="ttdeci">tvm::String out_layout</div><div class="ttdef"><b>Definition:</b> nn.h:219</div></div>
@@ -218,6 +217,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1BatchMatmulAttrs_html_a05710acb6565be899d567f642a26639a"><div class="ttname"><a href="structtvm_1_1relay_1_1BatchMatmulAttrs.html#a05710acb6565be899d567f642a26639a">tvm::relay::BatchMatmulAttrs::transpose_b</a></div><div class="ttdeci">bool transpose_b</div><div class="ttdef"><b>Definition:</b> nn.h:1113</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DAttrs.html">tvm::relay::Conv3DAttrs</a></div><div class="ttdoc">Attributes used in convolution operators. </div><div class="ttdef"><b>Definition:</b> nn.h:301</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1ConvWinogradWeightTransformAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1ConvWinogradWeightTransformAttrs.html">tvm::relay::ConvWinogradWeightTransformAttrs</a></div><div class="ttdoc">Attributes used in winograd weight transformation operators. </div><div class="ttdef"><b>Definition:</b> nn.h:187</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_a1263b2f122ed56faa812c76ecc115870"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a1263b2f122ed56faa812c76ecc115870">tvm::relay::Conv3DTransposeAttrs::data_layout</a></div><div class="ttdeci">tvm::String data_layout</div><div class="ttdef"><b>Definition:</b> nn.h:380</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1GroupNormAttrs_html_a2165c96ef2ed384d614246653edf2c00"><div class="ttname"><a href="structtvm_1_1relay_1_1GroupNormAttrs.html#a2165c96ef2ed384d614246653edf2c00">tvm::relay::GroupNormAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GroupNormAttrs, "relay.attrs.GroupNormAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:1372</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1AvgPool1DAttrs_html_acb0a059c91e3319df4926370184a8d49"><div class="ttname"><a href="structtvm_1_1relay_1_1AvgPool1DAttrs.html#acb0a059c91e3319df4926370184a8d49">tvm::relay::AvgPool1DAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(AvgPool1DAttrs, "relay.attrs.AvgPool1DAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:924</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DAttrs_html_ac4df94aff84232fa20163f8524cedba6"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DAttrs.html#ac4df94aff84232fa20163f8524cedba6">tvm::relay::Conv3DAttrs::padding</a></div><div class="ttdeci">Array< IndexExpr > padding</div><div class="ttdef"><b>Definition:</b> nn.h:303</div></div>
@@ -274,6 +274,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DAttrs_html_a0abda4529b2de9f35999ad5b5ccff870"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DAttrs.html#a0abda4529b2de9f35999ad5b5ccff870">tvm::relay::Conv2DAttrs::out_dtype</a></div><div class="ttdeci">DataType out_dtype</div><div class="ttdef"><b>Definition:</b> nn.h:128</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv1DTransposeAttrs_html_a7d9be6d3a1cd41d1e72deef333ce558d"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv1DTransposeAttrs.html#a7d9be6d3a1cd41d1e72deef333ce558d">tvm::relay::Conv1DTransposeAttrs::out_layout</a></div><div class="ttdeci">std::string out_layout</div><div class="ttdef"><b>Definition:</b> nn.h:629</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1AvgPool2DAttrs_html_a2d31fc1bf068402da8da7faaa6fcc373"><div class="ttname"><a href="structtvm_1_1relay_1_1AvgPool2DAttrs.html#a2d31fc1bf068402da8da7faaa6fcc373">tvm::relay::AvgPool2DAttrs::dilation</a></div><div class="ttdeci">Array< IndexExpr > dilation</div><div class="ttdef"><b>Definition:</b> nn.h:736</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_a7a3159f55dd2eaf15361d92f573fa19f"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a7a3159f55dd2eaf15361d92f573fa19f">tvm::relay::Conv3DTransposeAttrs::kernel_layout</a></div><div class="ttdeci">tvm::String kernel_layout</div><div class="ttdef"><b>Definition:</b> nn.h:381</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1DeformableConv2DAttrs_html_a8c741a4815d5bb4a6573dd0b9edc3143"><div class="ttname"><a href="structtvm_1_1relay_1_1DeformableConv2DAttrs.html#a8c741a4815d5bb4a6573dd0b9edc3143">tvm::relay::DeformableConv2DAttrs::kernel_layout</a></div><div class="ttdeci">std::string kernel_layout</div><div class="ttdef"><b>Definition:</b> nn.h:1426</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1MatmulAttrs_html_a55a176ca5d1e244203bc61a8ae780ae5"><div class="ttname"><a href="structtvm_1_1relay_1_1MatmulAttrs.html#a55a176ca5d1e244203bc61a8ae780ae5">tvm::relay::MatmulAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(MatmulAttrs, "relay.attrs.MatmulAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:1056</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SparseDenseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseDenseAttrs.html">tvm::relay::SparseDenseAttrs</a></div><div class="ttdoc">Attributes for sparse_dense operator. </div><div class="ttdef"><b>Definition:</b> nn.h:1133</div></div>
@@ -295,7 +296,6 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1UpSampling3DAttrs_html_a270613b4109d2b24766b7bfbac2539c1"><div class="ttname"><a href="structtvm_1_1relay_1_1UpSampling3DAttrs.html#a270613b4109d2b24766b7bfbac2539c1">tvm::relay::UpSampling3DAttrs::scale_w</a></div><div class="ttdeci">double scale_w</div><div class="ttdef"><b>Definition:</b> nn.h:1208</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DTransposeAttrs_html_a213669808996d6761fcc811bcc9e9ed6"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a213669808996d6761fcc811bcc9e9ed6">tvm::relay::Conv2DTransposeAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(Conv2DTransposeAttrs, "relay.attrs.Conv2DTransposeAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:543</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1BatchToSpaceNDAttrs_html_a44b4115b636c2b843949af36bc7c8087"><div class="ttname"><a href="structtvm_1_1relay_1_1BatchToSpaceNDAttrs.html#a44b4115b636c2b843949af36bc7c8087">tvm::relay::BatchToSpaceNDAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(BatchToSpaceNDAttrs, "relay.attrs.BatchToSpaceNDAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:1562</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_a4c7843b55a08d35ac511ff2bcabe3b00"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a4c7843b55a08d35ac511ff2bcabe3b00">tvm::relay::Conv3DTransposeAttrs::kernel_layout</a></div><div class="ttdeci">std::string kernel_layout</div><div class="ttdef"><b>Definition:</b> nn.h:381</div></div>
<div class="ttc" id="namespacetvm_html_a28c693333c2b15702b1a9a57dec0fbf5"><div class="ttname"><a href="namespacetvm.html#a28c693333c2b15702b1a9a57dec0fbf5">tvm::NullValue< DataType ></a></div><div class="ttdeci">DataType NullValue< DataType >()</div><div class="ttdef"><b>Definition:</b> attrs.h:90</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1GroupNormAttrs_html_aafc02cdca5286cca8ee5c7f23cf091ba"><div class="ttname"><a href="structtvm_1_1relay_1_1GroupNormAttrs.html#aafc02cdca5286cca8ee5c7f23cf091ba">tvm::relay::GroupNormAttrs::scale</a></div><div class="ttdeci">bool scale</div><div class="ttdef"><b>Definition:</b> nn.h:1370</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1LayerNormAttrs_html_aa4fbf81a614acfbea404e7d270c83685"><div class="ttname"><a href="structtvm_1_1relay_1_1LayerNormAttrs.html#aa4fbf81a614acfbea404e7d270c83685">tvm::relay::LayerNormAttrs::axis</a></div><div class="ttdeci">int axis</div><div class="ttdef"><b>Definition:</b> nn.h:1347</div></div>
@@ -316,7 +316,6 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1DenseAttrs_html"><div class="ttname"><a href="structtvm_1_1relay_1_1DenseAttrs.html">tvm::relay::DenseAttrs</a></div><div class="ttdoc">Attributes for dense operator. </div><div class="ttdef"><b>Definition:</b> nn.h:1075</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1MaxPool2DAttrs_html_a40f8ca285721a1a69b37ab630d601632"><div class="ttname"><a href="structtvm_1_1relay_1_1MaxPool2DAttrs.html#a40f8ca285721a1a69b37ab630d601632">tvm::relay::MaxPool2DAttrs::ceil_mode</a></div><div class="ttdeci">bool ceil_mode</div><div class="ttdef"><b>Definition:</b> nn.h:696</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DWinogradAttrs_html_a03bebdc912a86eaabe92f4dd74b09ba9"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DWinogradAttrs.html#a03bebdc912a86eaabe92f4dd74b09ba9">tvm::relay::Conv3DWinogradAttrs::groups</a></div><div class="ttdeci">int groups</div><div class="ttdef"><b>Definition:</b> nn.h:453</div></div>
-<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_a96a9fb507c88d5982ea434b64dd06039"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a96a9fb507c88d5982ea434b64dd06039">tvm::relay::Conv3DTransposeAttrs::out_layout</a></div><div class="ttdeci">std::string out_layout</div><div class="ttdef"><b>Definition:</b> nn.h:382</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DAttrs_html_ab50b191a7b0be9de1b08f12030791d4b"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DAttrs.html#ab50b191a7b0be9de1b08f12030791d4b">tvm::relay::Conv2DAttrs::kernel_layout</a></div><div class="ttdeci">tvm::String kernel_layout</div><div class="ttdef"><b>Definition:</b> nn.h:125</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1GlobalPool2DAttrs_html_a3891179803dcc37c729a6bab6df60c99"><div class="ttname"><a href="structtvm_1_1relay_1_1GlobalPool2DAttrs.html#a3891179803dcc37c729a6bab6df60c99">tvm::relay::GlobalPool2DAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(GlobalPool2DAttrs, "relay.attrs.GlobalPool2DAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:783</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_aa4dd3ea9f1eadf621f30533690585649"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#aa4dd3ea9f1eadf621f30533690585649">tvm::relay::Conv3DTransposeAttrs::dilation</a></div><div class="ttdeci">Array< IndexExpr > dilation</div><div class="ttdef"><b>Definition:</b> nn.h:378</div></div>
@@ -392,6 +391,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1relay_1_1SparseConv2DAttrs_html_a374d84740230bd86312cb5b2d0e96016"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseConv2DAttrs.html#a374d84740230bd86312cb5b2d0e96016">tvm::relay::SparseConv2DAttrs::kernel_size</a></div><div class="ttdeci">Array< IndexExpr > kernel_size</div><div class="ttdef"><b>Definition:</b> nn.h:1153</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1GroupNormAttrs_html_ad5489755171031cd0547b487b3aa6604"><div class="ttname"><a href="structtvm_1_1relay_1_1GroupNormAttrs.html#ad5489755171031cd0547b487b3aa6604">tvm::relay::GroupNormAttrs::epsilon</a></div><div class="ttdeci">double epsilon</div><div class="ttdef"><b>Definition:</b> nn.h:1368</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DTransposeAttrs_html_a2cca4ce8d1729231cb667f810a14ba77"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DTransposeAttrs.html#a2cca4ce8d1729231cb667f810a14ba77">tvm::relay::Conv2DTransposeAttrs::strides</a></div><div class="ttdeci">Array< IndexExpr > strides</div><div class="ttdef"><b>Definition:</b> nn.h:533</div></div>
+<div class="ttc" id="structtvm_1_1relay_1_1Conv3DTransposeAttrs_html_ac0c55c6ed61b2a425f5cfaa191f3470e"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#ac0c55c6ed61b2a425f5cfaa191f3470e">tvm::relay::Conv3DTransposeAttrs::out_layout</a></div><div class="ttdeci">tvm::String out_layout</div><div class="ttdef"><b>Definition:</b> nn.h:382</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1PReluAttrs_html_afb126b8cbdd8afad374eda19a71d7974"><div class="ttname"><a href="structtvm_1_1relay_1_1PReluAttrs.html#afb126b8cbdd8afad374eda19a71d7974">tvm::relay::PReluAttrs::TVM_DECLARE_ATTRS</a></div><div class="ttdeci">TVM_DECLARE_ATTRS(PReluAttrs, "relay.attrs.PReluAttrs")</div><div class="ttdef"><b>Definition:</b> nn.h:1285</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1Conv2DWinogradAttrs_html_a15350be67dd9492f29b828660a3f7a5f"><div class="ttname"><a href="structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a15350be67dd9492f29b828660a3f7a5f">tvm::relay::Conv2DWinogradAttrs::data_layout</a></div><div class="ttdeci">tvm::String data_layout</div><div class="ttdef"><b>Definition:</b> nn.h:217</div></div>
<div class="ttc" id="structtvm_1_1relay_1_1SparseConv2DAttrs_html_a60f43b99bf2cd3b54500e629086ec46e"><div class="ttname"><a href="structtvm_1_1relay_1_1SparseConv2DAttrs.html#a60f43b99bf2cd3b54500e629086ec46e">tvm::relay::SparseConv2DAttrs::layout</a></div><div class="ttdeci">std::string layout</div><div class="ttdef"><b>Definition:</b> nn.h:1152</div></div>
diff --git a/docs/reference/api/doxygen/search/all_10.js b/docs/reference/api/doxygen/search/all_10.js
index 0a7bcff3b..f8f51b8de 100644
--- a/docs/reference/api/doxygen/search/all_10.js
+++ b/docs/reference/api/doxygen/search/all_10.js
@@ -134,7 +134,7 @@ var searchData=
['original_5fvariables',['original_variables',['../classtvm_1_1te_1_1TransformNode.html#abc94c207521c4841843edd028aefcaeb',1,'tvm::te::TransformNode']]],
['ornode',['OrNode',['../classtvm_1_1tir_1_1OrNode.html',1,'tvm::tir']]],
['out_5fdtype',['out_dtype',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a3b3627df5ec9e23a15a0ae027168d77a',1,'tvm::relay::BinaryConv2DAttrs::out_dtype()'],['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#a8a391a620450d8c0e4449774a60272c6',1,'tvm::relay::BinaryDenseAttrs::out_dtype()'],['../structtvm_1_1relay_1_1Resize1DAttrs.html#a9c4fbee136d2238404a8223fd915f824',1,'tvm::relay::Resize1DAttrs::out_dtype()'],['../structtvm_1_1relay_1_1Resize2DAttrs.html#a2bf0c2451445a4961ec1098da1 [...]
- ['out_5flayout',['out_layout',['../structtvm_1_1relay_1_1Conv1DAttrs.html#af7efbed153b391a0f3c424b1d4beb1cc',1,'tvm::relay::Conv1DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a31671c2abaf2ae21b0a5622f992dbca9',1,'tvm::relay::Conv2DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4',1,'tvm::relay::Conv2DWinogradAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6' [...]
+ ['out_5flayout',['out_layout',['../structtvm_1_1relay_1_1Conv1DAttrs.html#af7efbed153b391a0f3c424b1d4beb1cc',1,'tvm::relay::Conv1DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a31671c2abaf2ae21b0a5622f992dbca9',1,'tvm::relay::Conv2DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4',1,'tvm::relay::Conv2DWinogradAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6' [...]
['out_5fshape',['out_shape',['../structtvm_1_1relay_1_1ThreefryGenerateAttrs.html#ab02111fe352ae6d124dfcb551d2626d1',1,'tvm::relay::ThreefryGenerateAttrs::out_shape()'],['../structtvm_1_1relay_1_1UniformAttrs.html#a1fc1dab6f15a36301b551ba1697d6c88',1,'tvm::relay::UniformAttrs::out_shape()'],['../structtvm_1_1relay_1_1NormalAttrs.html#a2e0e042f7b8afbe51e9ba4f571718cb7',1,'tvm::relay::NormalAttrs::out_shape()']]],
['outer',['outer',['../classtvm_1_1te_1_1SplitNode.html#a8d0f3974bbd80f360c717278ec932fbd',1,'tvm::te::SplitNode::outer()'],['../classtvm_1_1te_1_1FuseNode.html#a90efca7f5397eb34989f5d085ae9bab5',1,'tvm::te::FuseNode::outer()']]],
['output',['output',['../classtvm_1_1te_1_1Operation.html#a00b67945c799a2022d3164ab63dd3b82',1,'tvm::te::Operation']]],
diff --git a/docs/reference/api/doxygen/search/all_5.js b/docs/reference/api/doxygen/search/all_5.js
index 0e497f23a..622834723 100644
--- a/docs/reference/api/doxygen/search/all_5.js
+++ b/docs/reference/api/doxygen/search/all_5.js
@@ -4,7 +4,7 @@ var searchData=
['data_5f',['data_',['../classtvm_1_1runtime_1_1DenseMapNode.html#a58d530f3be4fac7ff99a574c2f6c8ddc',1,'tvm::runtime::DenseMapNode::data_()'],['../classtvm_1_1runtime_1_1ObjectRef.html#ac261cdb80487fb29ac42b28678f8cbef',1,'tvm::runtime::ObjectRef::data_()']]],
['data_5falignment',['data_alignment',['../classtvm_1_1tir_1_1BufferNode.html#aac30fc17abe8bde34272a854ba74b16a',1,'tvm::tir::BufferNode']]],
['data_5fbits',['data_bits',['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#a080c3768bc73266ef675953ea98c8ae8',1,'tvm::relay::BinaryDenseAttrs']]],
- ['data_5flayout',['data_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a6b952d430abee4b51035f2517523a6f8',1,'tvm::relay::BinaryConv2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71',1,'tvm::relay::Dilation2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#a98d365315eb243dcd3bf00c6f5d5703f',1,'tvm::relay::Conv1DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#acfe9a716dd05ea4c3cd36228 [...]
+ ['data_5flayout',['data_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a6b952d430abee4b51035f2517523a6f8',1,'tvm::relay::BinaryConv2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71',1,'tvm::relay::Dilation2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#a98d365315eb243dcd3bf00c6f5d5703f',1,'tvm::relay::Conv1DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#acfe9a716dd05ea4c3cd36228 [...]
['data_5flayout_2eh',['data_layout.h',['../data__layout_8h.html',1,'']]],
['data_5ftype_2eh',['data_type.h',['../data__type_8h.html',1,'']]],
['database',['Database',['../classtvm_1_1meta__schedule_1_1Database.html',1,'tvm::meta_schedule::Database'],['../classtvm_1_1meta__schedule_1_1ApplyHistoryBestNode.html#ae4c80b6dfe62636442a96bafb6887aa4',1,'tvm::meta_schedule::ApplyHistoryBestNode::database()'],['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#a9bc942d4fa3918753a1b036bb9373deb',1,'tvm::meta_schedule::TaskSchedulerNode::database()']]],
diff --git a/docs/reference/api/doxygen/search/all_c.js b/docs/reference/api/doxygen/search/all_c.js
index c6b07da47..2040cf482 100644
--- a/docs/reference/api/doxygen/search/all_c.js
+++ b/docs/reference/api/doxygen/search/all_c.js
@@ -73,7 +73,7 @@ var searchData=
['kelementwise',['kElementWise',['../namespacetvm_1_1topi.html#a0250c4095f19ae8a22ed85bc4ce5a40d',1,'tvm::topi']]],
['kelemwise',['kElemWise',['../namespacetvm_1_1relay.html#ab5f4d382bf1bee69c3e484ea6c837578a8c63d345994ce14eb197df6ad22de3aa',1,'tvm::relay']]],
['kembedinfo',['kEmbedInfo',['../namespacetvm_1_1tir.html#a8f4a86b205145696c0555fd02bd37f46a9d51682d02407dcdbbd4622cd54e4373',1,'tvm::tir']]],
- ['kernel_5flayout',['kernel_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#ada14efece2cacda93ed5f51141d0c55d',1,'tvm::relay::BinaryConv2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53',1,'tvm::relay::Dilation2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#aaec0a69ceb5121afd331270e363d5c4a',1,'tvm::relay::Conv1DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#ab50b191a7b0be9 [...]
+ ['kernel_5flayout',['kernel_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#ada14efece2cacda93ed5f51141d0c55d',1,'tvm::relay::BinaryConv2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53',1,'tvm::relay::Dilation2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#aaec0a69ceb5121afd331270e363d5c4a',1,'tvm::relay::Conv1DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#ab50b191a7b0be9 [...]
['kernel_5fsize',['kernel_size',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a03491f260db18ada216bb87e35931a49',1,'tvm::relay::BinaryConv2DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#ad22013a24dc10fc4442928ededba788e',1,'tvm::relay::Conv1DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a47a7d4f45d274e4f8012e6700b0eb18e',1,'tvm::relay::Conv2DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#aa54c9305b1858319e432f8d0 [...]
['kerror',['kError',['../namespacetvm.html#a908c332516a33fdc106cd9ee2ebc2b9eae3587c730cc1aa530fa4ddc9c4204e97',1,'tvm']]],
['kescapenop',['kEscapeNop',['../namespacetvm_1_1runtime_1_1micro__rpc.html#ae62577b404cccb2018ca8576b1f75bb6ab51cc55a54eb40e45e91baeb12213436',1,'tvm::runtime::micro_rpc']]],
diff --git a/docs/reference/api/doxygen/search/variables_4.js b/docs/reference/api/doxygen/search/variables_4.js
index 1b6a9feea..7fb264c6f 100644
--- a/docs/reference/api/doxygen/search/variables_4.js
+++ b/docs/reference/api/doxygen/search/variables_4.js
@@ -4,7 +4,7 @@ var searchData=
['data_5f',['data_',['../classtvm_1_1runtime_1_1DenseMapNode.html#a58d530f3be4fac7ff99a574c2f6c8ddc',1,'tvm::runtime::DenseMapNode::data_()'],['../classtvm_1_1runtime_1_1ObjectRef.html#ac261cdb80487fb29ac42b28678f8cbef',1,'tvm::runtime::ObjectRef::data_()']]],
['data_5falignment',['data_alignment',['../classtvm_1_1tir_1_1BufferNode.html#aac30fc17abe8bde34272a854ba74b16a',1,'tvm::tir::BufferNode']]],
['data_5fbits',['data_bits',['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#a080c3768bc73266ef675953ea98c8ae8',1,'tvm::relay::BinaryDenseAttrs']]],
- ['data_5flayout',['data_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a6b952d430abee4b51035f2517523a6f8',1,'tvm::relay::BinaryConv2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71',1,'tvm::relay::Dilation2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#a98d365315eb243dcd3bf00c6f5d5703f',1,'tvm::relay::Conv1DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#acfe9a716dd05ea4c3cd36228 [...]
+ ['data_5flayout',['data_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a6b952d430abee4b51035f2517523a6f8',1,'tvm::relay::BinaryConv2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#ac449ae6daf722a2d1826cac252368f71',1,'tvm::relay::Dilation2DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#a98d365315eb243dcd3bf00c6f5d5703f',1,'tvm::relay::Conv1DAttrs::data_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#acfe9a716dd05ea4c3cd36228 [...]
['database',['database',['../classtvm_1_1meta__schedule_1_1ApplyHistoryBestNode.html#ae4c80b6dfe62636442a96bafb6887aa4',1,'tvm::meta_schedule::ApplyHistoryBestNode::database()'],['../classtvm_1_1meta__schedule_1_1TaskSchedulerNode.html#a9bc942d4fa3918753a1b036bb9373deb',1,'tvm::meta_schedule::TaskSchedulerNode::database()']]],
['datatype_5ffields',['datatype_fields',['../structtvm_1_1runtime_1_1vm_1_1Instruction.html#a25adb383014a74a9c4ac805beefe86b6',1,'tvm::runtime::vm::Instruction']]],
['debug_5ffunc',['debug_func',['../structtvm_1_1relay_1_1DebugAttrs.html#aa57fc666a9674bdd94ad8e5ac4da18f7',1,'tvm::relay::DebugAttrs']]],
diff --git a/docs/reference/api/doxygen/search/variables_a.js b/docs/reference/api/doxygen/search/variables_a.js
index cf871ac24..bd4fcf4a1 100644
--- a/docs/reference/api/doxygen/search/variables_a.js
+++ b/docs/reference/api/doxygen/search/variables_a.js
@@ -25,7 +25,7 @@ var searchData=
['keepdims',['keepdims',['../structtvm_1_1relay_1_1ReduceAttrs.html#afa8f7f2b60bcb5c44f6cd3338d80143a',1,'tvm::relay::ReduceAttrs::keepdims()'],['../structtvm_1_1relay_1_1ArgReduceAttrs.html#a69a41c9cc211fe0a503ac89485517f35',1,'tvm::relay::ArgReduceAttrs::keepdims()'],['../structtvm_1_1relay_1_1VarianceAttrs.html#a35d1aaaa1f07c395f999eafb5a4ae60d',1,'tvm::relay::VarianceAttrs::keepdims()']]],
['keinsum',['kEinsum',['../namespacetvm_1_1topi.html#a6b33f2b888123f3ccd7191feeaedb93b',1,'tvm::topi']]],
['kelementwise',['kElementWise',['../namespacetvm_1_1topi.html#a0250c4095f19ae8a22ed85bc4ce5a40d',1,'tvm::topi']]],
- ['kernel_5flayout',['kernel_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#ada14efece2cacda93ed5f51141d0c55d',1,'tvm::relay::BinaryConv2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53',1,'tvm::relay::Dilation2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#aaec0a69ceb5121afd331270e363d5c4a',1,'tvm::relay::Conv1DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#ab50b191a7b0be9 [...]
+ ['kernel_5flayout',['kernel_layout',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#ada14efece2cacda93ed5f51141d0c55d',1,'tvm::relay::BinaryConv2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Dilation2DAttrs.html#aecf84f5da8bfbe44e0c90c72ce3a4a53',1,'tvm::relay::Dilation2DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#aaec0a69ceb5121afd331270e363d5c4a',1,'tvm::relay::Conv1DAttrs::kernel_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#ab50b191a7b0be9 [...]
['kernel_5fsize',['kernel_size',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a03491f260db18ada216bb87e35931a49',1,'tvm::relay::BinaryConv2DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv1DAttrs.html#ad22013a24dc10fc4442928ededba788e',1,'tvm::relay::Conv1DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a47a7d4f45d274e4f8012e6700b0eb18e',1,'tvm::relay::Conv2DAttrs::kernel_size()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#aa54c9305b1858319e432f8d0 [...]
['kexecutor',['kExecutor',['../namespacetvm_1_1attr.html#a688274c1d1bdf64c3a44c373c58ab06d',1,'tvm::attr']]],
['kexternalsymbol',['kExternalSymbol',['../namespacetvm_1_1relay_1_1attr.html#ae61f67fa7105e9ef262770ccc840cdb4',1,'tvm::relay::attr']]],
diff --git a/docs/reference/api/doxygen/search/variables_e.js b/docs/reference/api/doxygen/search/variables_e.js
index 2effad243..a3efd4fc6 100644
--- a/docs/reference/api/doxygen/search/variables_e.js
+++ b/docs/reference/api/doxygen/search/variables_e.js
@@ -17,7 +17,7 @@ var searchData=
['origin_5fop',['origin_op',['../classtvm_1_1te_1_1StageNode.html#a3e7c2fb80404a12a9e843fcb38accd78',1,'tvm::te::StageNode']]],
['original_5fvariables',['original_variables',['../classtvm_1_1te_1_1TransformNode.html#abc94c207521c4841843edd028aefcaeb',1,'tvm::te::TransformNode']]],
['out_5fdtype',['out_dtype',['../structtvm_1_1relay_1_1BinaryConv2DAttrs.html#a3b3627df5ec9e23a15a0ae027168d77a',1,'tvm::relay::BinaryConv2DAttrs::out_dtype()'],['../structtvm_1_1relay_1_1BinaryDenseAttrs.html#a8a391a620450d8c0e4449774a60272c6',1,'tvm::relay::BinaryDenseAttrs::out_dtype()'],['../structtvm_1_1relay_1_1Resize1DAttrs.html#a9c4fbee136d2238404a8223fd915f824',1,'tvm::relay::Resize1DAttrs::out_dtype()'],['../structtvm_1_1relay_1_1Resize2DAttrs.html#a2bf0c2451445a4961ec1098da1 [...]
- ['out_5flayout',['out_layout',['../structtvm_1_1relay_1_1Conv1DAttrs.html#af7efbed153b391a0f3c424b1d4beb1cc',1,'tvm::relay::Conv1DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a31671c2abaf2ae21b0a5622f992dbca9',1,'tvm::relay::Conv2DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4',1,'tvm::relay::Conv2DWinogradAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6' [...]
+ ['out_5flayout',['out_layout',['../structtvm_1_1relay_1_1Conv1DAttrs.html#af7efbed153b391a0f3c424b1d4beb1cc',1,'tvm::relay::Conv1DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DAttrs.html#a31671c2abaf2ae21b0a5622f992dbca9',1,'tvm::relay::Conv2DAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv2DWinogradAttrs.html#a6300f8aa97d520ad4a79d1071d821ec4',1,'tvm::relay::Conv2DWinogradAttrs::out_layout()'],['../structtvm_1_1relay_1_1Conv3DAttrs.html#a5c7385d50fc6c2ec7d7352a0b39d77c6' [...]
['out_5fshape',['out_shape',['../structtvm_1_1relay_1_1ThreefryGenerateAttrs.html#ab02111fe352ae6d124dfcb551d2626d1',1,'tvm::relay::ThreefryGenerateAttrs::out_shape()'],['../structtvm_1_1relay_1_1UniformAttrs.html#a1fc1dab6f15a36301b551ba1697d6c88',1,'tvm::relay::UniformAttrs::out_shape()'],['../structtvm_1_1relay_1_1NormalAttrs.html#a2e0e042f7b8afbe51e9ba4f571718cb7',1,'tvm::relay::NormalAttrs::out_shape()']]],
['outer',['outer',['../classtvm_1_1te_1_1SplitNode.html#a8d0f3974bbd80f360c717278ec932fbd',1,'tvm::te::SplitNode::outer()'],['../classtvm_1_1te_1_1FuseNode.html#a90efca7f5397eb34989f5d085ae9bab5',1,'tvm::te::FuseNode::outer()']]],
['output_5fformat',['output_format',['../structtvm_1_1relay_1_1AllClassNonMaximumSuppressionAttrs.html#ae91fadfed9949f446c3711bcc48ef844',1,'tvm::relay::AllClassNonMaximumSuppressionAttrs']]],
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs-members.html b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs-members.html
index 7d23be627..74ba622b5 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs-members.html
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs-members.html
@@ -79,7 +79,7 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af6aed95d70af7e44ce376a8d7be6c5f1">_type_index</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a8e4fd4e728774e0556cda84b0c2b80d6">_type_key</a></td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">static</span></td></tr>
<tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#aafd4b90da8ce3dae0252be77b904414f">channels</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5202a8aa859efcecab500f73304589fa">data_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a1263b2f122ed56faa812c76ecc115870">data_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a70fb5361147634605d6595bb89381f03">DecRef</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">protected</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#af4407d2b59132e803ff791482dbe0145">deleter_</a></td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">protected</span></td></tr>
<tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#aa4dd3ea9f1eadf621f30533690585649">dilation</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
@@ -92,7 +92,7 @@ $(function() {
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acfba199ef906818f35432d2e5532559a">InitByPackedArgs</a>(const runtime::TVMArgs &args, bool allow_unknown) final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< Conv3DTransposeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#abcc04a722102d16fd4d86f9b7dcdd1e1">InitBySeq</a>(Args &&... args)</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a90e90b3f4ba8a590baff78c75807bbc7">IsInstance</a>() const</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
- <tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a4c7843b55a08d35ac511ff2bcabe3b00">kernel_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
+ <tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a7a3159f55dd2eaf15361d92f573fa19f">kernel_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a6b3268e348827a2fa3b344a8c50bc4a0">kernel_size</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html#acefe615381b5d881870af9db7ce6a981">ListFieldInfo</a>() const final</td><td class="entry"><a class="el" href="classtvm_1_1AttrsNode.html">tvm::AttrsNode< Conv3DTransposeAttrs ></a></td><td class="entry"><span class="mlabel">inline</span><span class="mlabel">virtual</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a133436a9ec5c4a768b94102bf95a660b">Object</a>()</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
@@ -101,7 +101,7 @@ $(function() {
<tr><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#a69c32fbd96181f5c21d2c878ab285e4f">operator=</a>(const Object &other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr class="even"><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html#ae341e561272ff43cdcbc927bc29ac50d">operator=</a>(Object &&other)</td><td class="entry"><a class="el" href="classtvm_1_1runtime_1_1Object.html">tvm::runtime::Object</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
<tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a8b4cac395fbd82eede7561ffd6734022">out_dtype</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
- <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a96a9fb507c88d5982ea434b64dd06039">out_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
+ <tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#ac0c55c6ed61b2a425f5cfaa191f3470e">out_layout</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a488ff4efab5748d0de40669007374e6f">output_padding</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr class="even"><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5cab3105377ac668d03720ae221a10ea">padding</a></td><td class="entry"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html">tvm::relay::Conv3DTransposeAttrs</a></td><td class="entry"></td></tr>
<tr><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html#a80929190102473038bce5b4f6c42dff6">PrintDocString</a>(std::ostream &os) const</td><td class="entry"><a class="el" href="classtvm_1_1BaseAttrsNode.html">tvm::BaseAttrsNode</a></td><td class="entry"><span class="mlabel">inline</span></td></tr>
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs.html b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs.html
index 0430b1069..3bd91e1f1 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs.html
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs.html
@@ -84,7 +84,7 @@ Inheritance diagram for tvm::relay::Conv3DTransposeAttrs:</div>
<div class="dynheader">
Collaboration diagram for tvm::relay::Conv3DTransposeAttrs:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg" width="867" height="1944"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg" width="1016" height="1915"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
</div>
<table class="memberdecls">
@@ -160,12 +160,12 @@ Public Attributes</h2></td></tr>
<tr class="separator:aa4dd3ea9f1eadf621f30533690585649"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a88c1da90206712268beedd11ea10e88f"><td class="memItemLeft" align="right" valign="top">int </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a88c1da90206712268beedd11ea10e88f">groups</a></td></tr>
<tr class="separator:a88c1da90206712268beedd11ea10e88f"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a5202a8aa859efcecab500f73304589fa"><td class="memItemLeft" align="right" valign="top">std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a5202a8aa859efcecab500f73304589fa">data_layout</a></td></tr>
-<tr class="separator:a5202a8aa859efcecab500f73304589fa"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a4c7843b55a08d35ac511ff2bcabe3b00"><td class="memItemLeft" align="right" valign="top">std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a4c7843b55a08d35ac511ff2bcabe3b00">kernel_layout</a></td></tr>
-<tr class="separator:a4c7843b55a08d35ac511ff2bcabe3b00"><td class="memSeparator" colspan="2"> </td></tr>
-<tr class="memitem:a96a9fb507c88d5982ea434b64dd06039"><td class="memItemLeft" align="right" valign="top">std::string </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a96a9fb507c88d5982ea434b64dd06039">out_layout</a></td></tr>
-<tr class="separator:a96a9fb507c88d5982ea434b64dd06039"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a1263b2f122ed56faa812c76ecc115870"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a1263b2f122ed56faa812c76ecc115870">data_layout</a></td></tr>
+<tr class="separator:a1263b2f122ed56faa812c76ecc115870"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:a7a3159f55dd2eaf15361d92f573fa19f"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a7a3159f55dd2eaf15361d92f573fa19f">kernel_layout</a></td></tr>
+<tr class="separator:a7a3159f55dd2eaf15361d92f573fa19f"><td class="memSeparator" colspan="2"> </td></tr>
+<tr class="memitem:ac0c55c6ed61b2a425f5cfaa191f3470e"><td class="memItemLeft" align="right" valign="top"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#ac0c55c6ed61b2a425f5cfaa191f3470e">out_layout</a></td></tr>
+<tr class="separator:ac0c55c6ed61b2a425f5cfaa191f3470e"><td class="memSeparator" colspan="2"> </td></tr>
<tr class="memitem:a8b4cac395fbd82eede7561ffd6734022"><td class="memItemLeft" align="right" valign="top"><a class="el" href="namespacetvm.html#a41918af1a1dc386388639a9d3ad06c5d">DataType</a> </td><td class="memItemRight" valign="bottom"><a class="el" href="structtvm_1_1relay_1_1Conv3DTransposeAttrs.html#a8b4cac395fbd82eede7561ffd6734022">out_dtype</a></td></tr>
<tr class="separator:a8b4cac395fbd82eede7561ffd6734022"><td class="memSeparator" colspan="2"> </td></tr>
</table><table class="memberdecls">
@@ -296,14 +296,14 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a5202a8aa859efcecab500f73304589fa"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a5202a8aa859efcecab500f73304589fa">◆ </a></span>data_layout</h2>
+<a id="a1263b2f122ed56faa812c76ecc115870"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a1263b2f122ed56faa812c76ecc115870">◆ </a></span>data_layout</h2>
<div class="memitem">
<div class="memproto">
<table class="memname">
<tr>
- <td class="memname">std::string tvm::relay::Conv3DTransposeAttrs::data_layout</td>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> tvm::relay::Conv3DTransposeAttrs::data_layout</td>
</tr>
</table>
</div><div class="memdoc">
@@ -338,14 +338,14 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a4c7843b55a08d35ac511ff2bcabe3b00"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a4c7843b55a08d35ac511ff2bcabe3b00">◆ </a></span>kernel_layout</h2>
+<a id="a7a3159f55dd2eaf15361d92f573fa19f"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#a7a3159f55dd2eaf15361d92f573fa19f">◆ </a></span>kernel_layout</h2>
<div class="memitem">
<div class="memproto">
<table class="memname">
<tr>
- <td class="memname">std::string tvm::relay::Conv3DTransposeAttrs::kernel_layout</td>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> tvm::relay::Conv3DTransposeAttrs::kernel_layout</td>
</tr>
</table>
</div><div class="memdoc">
@@ -380,14 +380,14 @@ Additional Inherited Members</h2></td></tr>
</div>
</div>
-<a id="a96a9fb507c88d5982ea434b64dd06039"></a>
-<h2 class="memtitle"><span class="permalink"><a href="#a96a9fb507c88d5982ea434b64dd06039">◆ </a></span>out_layout</h2>
+<a id="ac0c55c6ed61b2a425f5cfaa191f3470e"></a>
+<h2 class="memtitle"><span class="permalink"><a href="#ac0c55c6ed61b2a425f5cfaa191f3470e">◆ </a></span>out_layout</h2>
<div class="memitem">
<div class="memproto">
<table class="memname">
<tr>
- <td class="memname">std::string tvm::relay::Conv3DTransposeAttrs::out_layout</td>
+ <td class="memname"><a class="el" href="classtvm_1_1runtime_1_1String.html">tvm::String</a> tvm::relay::Conv3DTransposeAttrs::out_layout</td>
</tr>
</table>
</div><div class="memdoc">
diff --git a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg
index c944dfa79..caddf4952 100644
--- a/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg
+++ b/docs/reference/api/doxygen/structtvm_1_1relay_1_1Conv3DTransposeAttrs__coll__graph.svg
@@ -4,323 +4,360 @@
<!-- Generated by graphviz version 2.40.1 (20161225.0304)
-->
<!-- Title: tvm::relay::Conv3DTransposeAttrs Pages: 1 -->
-<svg width="650pt" height="1458pt"
- viewBox="0.00 0.00 649.50 1458.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1454)">
+<svg width="762pt" height="1436pt"
+ viewBox="0.00 0.00 761.50 1436.00" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
+<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1432)">
<title>tvm::relay::Conv3DTransposeAttrs</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1454 645.5,-1454 645.5,4 -4,4"/>
+<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1432 757.5,-1432 757.5,4 -4,4"/>
<!-- Node4 -->
<g id="node1" class="node">
<title>Node4</title>
-<polygon fill="#bfbfbf" stroke="#000000" points="208,-.5 208,-101.5 367,-101.5 367,-.5 208,-.5"/>
-<text text-anchor="start" x="216" y="-89.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::relay::Conv3DTranspose</text>
-<text text-anchor="middle" x="287.5" y="-78.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Attrs</text>
-<polyline fill="none" stroke="#000000" points="208,-71.5 367,-71.5 "/>
-<text text-anchor="start" x="216" y="-59.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ groups</text>
-<text text-anchor="start" x="216" y="-48.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ data_layout</text>
-<text text-anchor="start" x="216" y="-37.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ kernel_layout</text>
-<text text-anchor="start" x="216" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ out_layout</text>
-<polyline fill="none" stroke="#000000" points="208,-19.5 367,-19.5 "/>
-<text text-anchor="start" x="216" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_ATTRS()</text>
+<polygon fill="#bfbfbf" stroke="#000000" points="335,-.5 335,-68.5 494,-68.5 494,-.5 335,-.5"/>
+<text text-anchor="start" x="343" y="-56.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::relay::Conv3DTranspose</text>
+<text text-anchor="middle" x="414.5" y="-45.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Attrs</text>
+<polyline fill="none" stroke="#000000" points="335,-38.5 494,-38.5 "/>
+<text text-anchor="start" x="343" y="-26.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ groups</text>
+<polyline fill="none" stroke="#000000" points="335,-19.5 494,-19.5 "/>
+<text text-anchor="start" x="343" y="-7.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_ATTRS()</text>
</g>
<!-- Node5 -->
<g id="node2" class="node">
<title>Node5</title>
<g id="a_node2"><a xlink:href="classtvm_1_1AttrsNode.html" target="_top" xlink:title="{tvm::AttrsNode\< Conv3DTranspose\lAttrs \>\n||+ VisitAttrs()\l+ VisitNonDefaultAttrs()\l+ InitByPackedArgs()\l+ SEqualReduce()\l+ SHashReduce()\l+ ListFieldInfo()\l}">
-<polygon fill="#ffffff" stroke="#000000" points="9,-215.5 9,-338.5 198,-338.5 198,-215.5 9,-215.5"/>
-<text text-anchor="start" x="17" y="-326.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::AttrsNode< Conv3DTranspose</text>
-<text text-anchor="middle" x="103.5" y="-315.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Attrs ></text>
-<polyline fill="none" stroke="#000000" points="9,-308.5 198,-308.5 "/>
-<text text-anchor="middle" x="103.5" y="-296.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="9,-289.5 198,-289.5 "/>
-<text text-anchor="start" x="17" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="17" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
-<text text-anchor="start" x="17" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
-<text text-anchor="start" x="17" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SEqualReduce()</text>
-<text text-anchor="start" x="17" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SHashReduce()</text>
-<text text-anchor="start" x="17" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
+<polygon fill="#ffffff" stroke="#000000" points="9,-182.5 9,-305.5 198,-305.5 198,-182.5 9,-182.5"/>
+<text text-anchor="start" x="17" y="-293.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::AttrsNode< Conv3DTranspose</text>
+<text text-anchor="middle" x="103.5" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">Attrs ></text>
+<polyline fill="none" stroke="#000000" points="9,-275.5 198,-275.5 "/>
+<text text-anchor="middle" x="103.5" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="9,-256.5 198,-256.5 "/>
+<text text-anchor="start" x="17" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="17" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
+<text text-anchor="start" x="17" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
+<text text-anchor="start" x="17" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SEqualReduce()</text>
+<text text-anchor="start" x="17" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ SHashReduce()</text>
+<text text-anchor="start" x="17" y="-189.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
</a>
</g>
</g>
<!-- Node5->Node4 -->
<g id="edge1" class="edge">
<title>Node5->Node4</title>
-<path fill="none" stroke="#191970" d="M152.8494,-206.7373C173.0444,-179.0803 197.1271,-147.4379 220.5,-120 225.6973,-113.8988 231.301,-107.6598 236.9761,-101.5491"/>
-<polygon fill="none" stroke="#191970" points="149.759,-205.0363 146.7119,-215.1835 155.4219,-209.1512 149.759,-205.0363"/>
+<path fill="none" stroke="#191970" d="M141.376,-173.7294C161.2034,-143.0033 188.1286,-109.0196 220.5,-87 254.2548,-64.0395 297.6779,-51.1002 334.8812,-43.8181"/>
+<polygon fill="none" stroke="#191970" points="138.347,-171.9711 135.9733,-182.2966 144.268,-175.7051 138.347,-171.9711"/>
</g>
<!-- Node6 -->
<g id="node3" class="node">
<title>Node6</title>
<g id="a_node3"><a xlink:href="classtvm_1_1BaseAttrsNode.html" target="_top" xlink:title="Base class of all attribute class. ">
-<polygon fill="#ffffff" stroke="#000000" points="0,-620.5 0,-798.5 207,-798.5 207,-620.5 0,-620.5"/>
-<text text-anchor="middle" x="103.5" y="-786.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseAttrsNode</text>
-<polyline fill="none" stroke="#000000" points="0,-779.5 207,-779.5 "/>
-<text text-anchor="start" x="8" y="-767.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="8" y="-756.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<polygon fill="#ffffff" stroke="#000000" points="0,-598.5 0,-776.5 207,-776.5 207,-598.5 0,-598.5"/>
+<text text-anchor="middle" x="103.5" y="-764.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseAttrsNode</text>
+<polyline fill="none" stroke="#000000" points="0,-757.5 207,-757.5 "/>
+<text text-anchor="start" x="8" y="-745.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
<text text-anchor="start" x="8" y="-734.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="8" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<polyline fill="none" stroke="#000000" points="0,-716.5 207,-716.5 "/>
-<text text-anchor="start" x="8" y="-704.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~BaseAttrsNode()</text>
-<text text-anchor="start" x="8" y="-693.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
-<text text-anchor="start" x="8" y="-682.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitBySeq()</text>
-<text text-anchor="start" x="8" y="-671.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrintDocString()</text>
-<text text-anchor="start" x="8" y="-660.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
-<text text-anchor="start" x="8" y="-649.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
-<text text-anchor="start" x="8" y="-638.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
-<text text-anchor="start" x="8" y="-627.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_BASE_OBJECT_INFO()</text>
+<text text-anchor="start" x="8" y="-723.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="8" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="8" y="-701.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<polyline fill="none" stroke="#000000" points="0,-694.5 207,-694.5 "/>
+<text text-anchor="start" x="8" y="-682.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~BaseAttrsNode()</text>
+<text text-anchor="start" x="8" y="-671.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitAttrs()</text>
+<text text-anchor="start" x="8" y="-660.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitBySeq()</text>
+<text text-anchor="start" x="8" y="-649.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrintDocString()</text>
+<text text-anchor="start" x="8" y="-638.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ VisitNonDefaultAttrs()</text>
+<text text-anchor="start" x="8" y="-627.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ListFieldInfo()</text>
+<text text-anchor="start" x="8" y="-616.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ InitByPackedArgs()</text>
+<text text-anchor="start" x="8" y="-605.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DECLARE_BASE_OBJECT_INFO()</text>
</a>
</g>
</g>
<!-- Node6->Node5 -->
<g id="edge2" class="edge">
<title>Node6->Node5</title>
-<path fill="none" stroke="#191970" d="M103.5,-610.3808C103.5,-526.7348 103.5,-409.6051 103.5,-338.762"/>
-<polygon fill="none" stroke="#191970" points="100.0001,-610.4101 103.5,-620.4101 107.0001,-610.4102 100.0001,-610.4101"/>
+<path fill="none" stroke="#191970" d="M103.5,-588.1758C103.5,-501.5905 103.5,-378.7352 103.5,-305.6272"/>
+<polygon fill="none" stroke="#191970" points="100.0001,-588.2846 103.5,-598.2847 107.0001,-588.2847 100.0001,-588.2846"/>
</g>
<!-- Node7 -->
<g id="node4" class="node">
<title>Node7</title>
<g id="a_node4"><a xlink:href="classtvm_1_1runtime_1_1Object.html" target="_top" xlink:title="base class of all object containers. ">
-<polygon fill="#ffffff" stroke="#000000" points="12,-836.5 12,-1223.5 195,-1223.5 195,-836.5 12,-836.5"/>
-<text text-anchor="middle" x="103.5" y="-1211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
-<polyline fill="none" stroke="#000000" points="12,-1204.5 195,-1204.5 "/>
-<text text-anchor="start" x="20" y="-1192.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
-<text text-anchor="start" x="20" y="-1181.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
-<text text-anchor="start" x="20" y="-1170.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
-<text text-anchor="start" x="20" y="-1159.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
-<text text-anchor="start" x="20" y="-1148.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
-<text text-anchor="start" x="20" y="-1137.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
-<text text-anchor="start" x="20" y="-1126.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
-<text text-anchor="start" x="20" y="-1115.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
-<text text-anchor="start" x="20" y="-1104.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="20" y="-1093.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<polygon fill="#ffffff" stroke="#000000" points="12,-814.5 12,-1201.5 195,-1201.5 195,-814.5 12,-814.5"/>
+<text text-anchor="middle" x="103.5" y="-1189.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Object</text>
+<polyline fill="none" stroke="#000000" points="12,-1182.5 195,-1182.5 "/>
+<text text-anchor="start" x="20" y="-1170.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_key</text>
+<text text-anchor="start" x="20" y="-1159.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_final</text>
+<text text-anchor="start" x="20" y="-1148.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots</text>
+<text text-anchor="start" x="20" y="-1137.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_child_slots_can</text>
+<text text-anchor="start" x="20" y="-1126.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_overflow</text>
+<text text-anchor="start" x="20" y="-1115.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_visit</text>
+<text text-anchor="start" x="20" y="-1104.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_attrs</text>
+<text text-anchor="start" x="20" y="-1093.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_sequal</text>
<text text-anchor="start" x="20" y="-1082.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
-<text text-anchor="start" x="20" y="-1071.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
-<text text-anchor="start" x="20" y="-1060.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
-<text text-anchor="start" x="20" y="-1049.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
-<polyline fill="none" stroke="#000000" points="12,-1042.5 195,-1042.5 "/>
-<text text-anchor="start" x="20" y="-1030.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
-<text text-anchor="start" x="20" y="-1019.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
-<text text-anchor="start" x="20" y="-1008.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
-<text text-anchor="start" x="20" y="-997.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
-<text text-anchor="start" x="20" y="-986.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="20" y="-975.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="20" y="-964.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="20" y="-1071.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_has_method_shash</text>
+<text text-anchor="start" x="20" y="-1060.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_reduce</text>
+<text text-anchor="start" x="20" y="-1049.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_index</text>
+<text text-anchor="start" x="20" y="-1038.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># type_index_</text>
+<text text-anchor="start" x="20" y="-1027.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># ref_counter_</text>
+<polyline fill="none" stroke="#000000" points="12,-1020.5 195,-1020.5 "/>
+<text text-anchor="start" x="20" y="-1008.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ type_index()</text>
+<text text-anchor="start" x="20" y="-997.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKey()</text>
+<text text-anchor="start" x="20" y="-986.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ GetTypeKeyHash()</text>
+<text text-anchor="start" x="20" y="-975.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ IsInstance()</text>
+<text text-anchor="start" x="20" y="-964.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
<text text-anchor="start" x="20" y="-953.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
-<text text-anchor="start" x="20" y="-942.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="20" y="-931.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="20" y="-920.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
-<text text-anchor="start" x="20" y="-909.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
-<text text-anchor="start" x="20" y="-898.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
-<text text-anchor="start" x="20" y="-887.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
-<text text-anchor="start" x="20" y="-876.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
-<text text-anchor="start" x="20" y="-865.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
-<text text-anchor="start" x="20" y="-854.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
-<text text-anchor="start" x="20" y="-843.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-942.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="20" y="-931.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Object()</text>
+<text text-anchor="start" x="20" y="-920.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="20" y="-909.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="20" y="-898.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2Key()</text>
+<text text-anchor="start" x="20" y="-887.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeIndex2KeyHash()</text>
+<text text-anchor="start" x="20" y="-876.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TypeKey2Index()</text>
+<text text-anchor="start" x="20" y="-865.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _GetOrAllocRuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-854.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ RuntimeTypeIndex()</text>
+<text text-anchor="start" x="20" y="-843.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># IncRef()</text>
+<text text-anchor="start" x="20" y="-832.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DecRef()</text>
+<text text-anchor="start" x="20" y="-821.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetOrAllocRuntimeTypeIndex()</text>
</a>
</g>
</g>
<!-- Node7->Node6 -->
<g id="edge3" class="edge">
<title>Node7->Node6</title>
-<path fill="none" stroke="#191970" d="M103.5,-825.9464C103.5,-816.5963 103.5,-807.4618 103.5,-798.684"/>
-<polygon fill="none" stroke="#191970" points="100.0001,-826.1701 103.5,-836.1701 107.0001,-826.1701 100.0001,-826.1701"/>
+<path fill="none" stroke="#191970" d="M103.5,-803.9464C103.5,-794.5963 103.5,-785.4618 103.5,-776.684"/>
+<polygon fill="none" stroke="#191970" points="100.0001,-804.1701 103.5,-814.1701 107.0001,-804.1701 100.0001,-804.1701"/>
</g>
<!-- Node7->Node7 -->
<g id="edge4" class="edge">
<title>Node7->Node7</title>
-<path fill="none" stroke="#404040" d="M195.3625,-1063.9248C206.0482,-1057.6637 213,-1046.3555 213,-1030 213,-1019.0112 209.8618,-1010.3007 204.5615,-1003.8687"/>
-<polygon fill="none" stroke="#404040" points="204.5184,-1003.8322 197.3548,-1003.0056 195.3625,-996.0752 202.5261,-996.9017 204.5184,-1003.8322"/>
-<text text-anchor="middle" x="239" y="-1027.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
+<path fill="none" stroke="#404040" d="M195.3625,-1041.9248C206.0482,-1035.6637 213,-1024.3555 213,-1008 213,-997.0112 209.8618,-988.3007 204.5615,-981.8687"/>
+<polygon fill="none" stroke="#404040" points="204.5184,-981.8322 197.3548,-981.0056 195.3625,-974.0752 202.5261,-974.9017 204.5184,-981.8322"/>
+<text text-anchor="middle" x="239" y="-1005.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #deleter_</text>
</g>
<!-- Node8 -->
<g id="node5" class="node">
<title>Node8</title>
<g id="a_node5"><a xlink:href="classtvm_1_1runtime_1_1Array.html" target="_top" xlink:title="{tvm::runtime::Array\l\< tvm::PrimExpr \>\n||+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ Array()\l+ operator=()\l+ operator=()\land 24 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="193,-423.5 193,-601.5 306,-601.5 306,-423.5 193,-423.5"/>
-<text text-anchor="start" x="201" y="-589.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
-<text text-anchor="middle" x="249.5" y="-578.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::PrimExpr ></text>
-<polyline fill="none" stroke="#000000" points="193,-571.5 306,-571.5 "/>
-<text text-anchor="middle" x="249.5" y="-559.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="193,-552.5 306,-552.5 "/>
-<text text-anchor="start" x="201" y="-540.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-529.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-518.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-507.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-496.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-485.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-474.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-463.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
-<text text-anchor="start" x="201" y="-452.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="201" y="-441.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
-<text text-anchor="start" x="201" y="-430.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
+<polygon fill="#ffffff" stroke="#000000" points="197,-396 197,-574 310,-574 310,-396 197,-396"/>
+<text text-anchor="start" x="205" y="-562" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::Array</text>
+<text text-anchor="middle" x="253.5" y="-551" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::PrimExpr ></text>
+<polyline fill="none" stroke="#000000" points="197,-544 310,-544 "/>
+<text text-anchor="middle" x="253.5" y="-532" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="197,-525 310,-525 "/>
+<text text-anchor="start" x="205" y="-513" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-502" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-491" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-480" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-469" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-458" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-447" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-436" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Array()</text>
+<text text-anchor="start" x="205" y="-425" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="205" y="-414" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="205" y="-403" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 24 more...</text>
</a>
</g>
</g>
<!-- Node8->Node4 -->
<g id="edge5" class="edge">
<title>Node8->Node4</title>
-<path fill="none" stroke="#404040" d="M236.9089,-423.2705C229.0676,-349.0101 223.8036,-240.9574 243.5,-149 246.0901,-136.9077 250.2904,-124.5048 255.0929,-112.7634"/>
-<polygon fill="none" stroke="#404040" points="255.0949,-112.7588 253.7993,-105.665 259.8491,-101.7407 261.1447,-108.8345 255.0949,-112.7588"/>
-<text text-anchor="middle" x="286" y="-296.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +kernel_size</text>
-<text text-anchor="middle" x="286" y="-285.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+strides</text>
-<text text-anchor="middle" x="286" y="-274.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+dilation</text>
-<text text-anchor="middle" x="286" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+output_padding</text>
-<text text-anchor="middle" x="286" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+padding</text>
+<path fill="none" stroke="#404040" d="M224.915,-395.6897C205.1424,-316.0392 190.8238,-199.4591 243.5,-116 261.5564,-87.3918 292.712,-68.6154 323.5242,-56.3885"/>
+<polygon fill="none" stroke="#404040" points="323.5907,-56.3638 327.8166,-50.5207 334.8356,-52.1741 330.6097,-58.0173 323.5907,-56.3638"/>
+<text text-anchor="middle" x="286" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +kernel_size</text>
+<text text-anchor="middle" x="286" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+strides</text>
+<text text-anchor="middle" x="286" y="-241.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+dilation</text>
+<text text-anchor="middle" x="286" y="-230.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+output_padding</text>
+<text text-anchor="middle" x="286" y="-219.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+padding</text>
</g>
<!-- Node9 -->
<g id="node6" class="node">
<title>Node9</title>
<g id="a_node6"><a xlink:href="classtvm_1_1runtime_1_1ObjectRef.html" target="_top" xlink:title="Base class of all object reference. ">
-<polygon fill="#ffffff" stroke="#000000" points="315.5,-919 315.5,-1141 449.5,-1141 449.5,-919 315.5,-919"/>
-<text text-anchor="middle" x="382.5" y="-1129" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
-<polyline fill="none" stroke="#000000" points="315.5,-1122 449.5,-1122 "/>
-<text text-anchor="start" x="323.5" y="-1110" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
-<polyline fill="none" stroke="#000000" points="315.5,-1103 449.5,-1103 "/>
-<text text-anchor="start" x="323.5" y="-1091" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="323.5" y="-1080" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
-<text text-anchor="start" x="323.5" y="-1069" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
-<text text-anchor="start" x="323.5" y="-1058" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
-<text text-anchor="start" x="323.5" y="-1047" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
-<text text-anchor="start" x="323.5" y="-1036" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
-<text text-anchor="start" x="323.5" y="-1025" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
-<text text-anchor="start" x="323.5" y="-1014" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="323.5" y="-1003" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="323.5" y="-992" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
-<text text-anchor="start" x="323.5" y="-981" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
-<text text-anchor="start" x="323.5" y="-970" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
-<text text-anchor="start" x="323.5" y="-959" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
-<text text-anchor="start" x="323.5" y="-948" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
-<text text-anchor="start" x="323.5" y="-937" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
-<text text-anchor="start" x="323.5" y="-926" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
+<polygon fill="#ffffff" stroke="#000000" points="347.5,-897 347.5,-1119 481.5,-1119 481.5,-897 347.5,-897"/>
+<text text-anchor="middle" x="414.5" y="-1107" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectRef</text>
+<polyline fill="none" stroke="#000000" points="347.5,-1100 481.5,-1100 "/>
+<text text-anchor="start" x="355.5" y="-1088" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ _type_is_nullable</text>
+<polyline fill="none" stroke="#000000" points="347.5,-1081 481.5,-1081 "/>
+<text text-anchor="start" x="355.5" y="-1069" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="355.5" y="-1058" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectRef()</text>
+<text text-anchor="start" x="355.5" y="-1047" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ same_as()</text>
+<text text-anchor="start" x="355.5" y="-1036" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator==()</text>
+<text text-anchor="start" x="355.5" y="-1025" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator!=()</text>
+<text text-anchor="start" x="355.5" y="-1014" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator<()</text>
+<text text-anchor="start" x="355.5" y="-1003" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ defined()</text>
+<text text-anchor="start" x="355.5" y="-992" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="355.5" y="-981" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="355.5" y="-970" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ unique()</text>
+<text text-anchor="start" x="355.5" y="-959" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ use_count()</text>
+<text text-anchor="start" x="355.5" y="-948" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ as()</text>
+<text text-anchor="start" x="355.5" y="-937" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># get_mutable()</text>
+<text text-anchor="start" x="355.5" y="-926" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># DowncastNoCheck()</text>
+<text text-anchor="start" x="355.5" y="-915" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># FFIClearAfterMove()</text>
+<text text-anchor="start" x="355.5" y="-904" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"># GetDataPtr()</text>
</a>
</g>
</g>
<!-- Node9->Node8 -->
<g id="edge6" class="edge">
<title>Node9->Node8</title>
-<path fill="none" stroke="#191970" d="M349.526,-908.9013C340.0177,-873.5123 329.7239,-834.7403 320.5,-799 303.4685,-733.0076 284.97,-658.2554 271.1258,-601.6576"/>
-<polygon fill="none" stroke="#191970" points="346.2079,-910.0403 352.1855,-918.7878 352.9676,-908.2219 346.2079,-910.0403"/>
+<path fill="none" stroke="#191970" d="M366.9229,-887.5184C353.7061,-852.1697 339.8733,-813.2646 328.5,-777 307.3945,-709.7039 287.7278,-632.3505 273.8328,-574.1727"/>
+<polygon fill="none" stroke="#191970" points="363.656,-888.7748 370.4491,-896.9052 370.2088,-886.3131 363.656,-888.7748"/>
</g>
<!-- Node12 -->
<g id="node9" class="node">
<title>Node12</title>
<g id="a_node9"><a xlink:href="classtvm_1_1BaseExpr.html" target="_top" xlink:title="Managed reference to BaseExprNode. ">
-<polygon fill="#ffffff" stroke="#000000" points="329.5,-675.5 329.5,-743.5 483.5,-743.5 483.5,-675.5 329.5,-675.5"/>
-<text text-anchor="middle" x="406.5" y="-731.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseExpr</text>
-<polyline fill="none" stroke="#000000" points="329.5,-724.5 483.5,-724.5 "/>
-<text text-anchor="middle" x="406.5" y="-712.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="329.5,-705.5 483.5,-705.5 "/>
-<text text-anchor="start" x="337.5" y="-693.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="337.5" y="-682.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="337.5,-653.5 337.5,-721.5 491.5,-721.5 491.5,-653.5 337.5,-653.5"/>
+<text text-anchor="middle" x="414.5" y="-709.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::BaseExpr</text>
+<polyline fill="none" stroke="#000000" points="337.5,-702.5 491.5,-702.5 "/>
+<text text-anchor="middle" x="414.5" y="-690.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="337.5,-683.5 491.5,-683.5 "/>
+<text text-anchor="start" x="345.5" y="-671.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="345.5" y="-660.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
</a>
</g>
</g>
<!-- Node9->Node12 -->
<g id="edge10" class="edge">
<title>Node9->Node12</title>
-<path fill="none" stroke="#191970" d="M391.5885,-908.6302C396.0137,-849.5356 401.0011,-782.9337 403.9405,-743.6805"/>
-<polygon fill="none" stroke="#191970" points="388.0833,-908.5707 390.8267,-918.8041 395.0637,-909.0934 388.0833,-908.5707"/>
+<path fill="none" stroke="#191970" d="M414.5,-886.6302C414.5,-827.5356 414.5,-760.9337 414.5,-721.6805"/>
+<polygon fill="none" stroke="#191970" points="411.0001,-886.8041 414.5,-896.8041 418.0001,-886.8042 411.0001,-886.8041"/>
+</g>
+<!-- Node13 -->
+<g id="node10" class="node">
+<title>Node13</title>
+<g id="a_node10"><a xlink:href="classtvm_1_1runtime_1_1String.html" target="_top" xlink:title="Reference to string objects. ">
+<polygon fill="#ffffff" stroke="#000000" points="467.5,-390.5 467.5,-579.5 583.5,-579.5 583.5,-390.5 467.5,-390.5"/>
+<text text-anchor="middle" x="525.5" y="-567.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::String</text>
+<polyline fill="none" stroke="#000000" points="467.5,-560.5 583.5,-560.5 "/>
+<text text-anchor="middle" x="525.5" y="-548.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="467.5,-541.5 583.5,-541.5 "/>
+<text text-anchor="start" x="475.5" y="-529.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ String()</text>
+<text text-anchor="start" x="475.5" y="-518.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ String()</text>
+<text text-anchor="start" x="475.5" y="-507.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ String()</text>
+<text text-anchor="start" x="475.5" y="-496.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ String()</text>
+<text text-anchor="start" x="475.5" y="-485.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="475.5" y="-474.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator=()</text>
+<text text-anchor="start" x="475.5" y="-463.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ compare()</text>
+<text text-anchor="start" x="475.5" y="-452.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ compare()</text>
+<text text-anchor="start" x="475.5" y="-441.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ compare()</text>
+<text text-anchor="start" x="475.5" y="-430.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ c_str()</text>
+<text text-anchor="start" x="475.5" y="-419.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 7 more...</text>
+<text text-anchor="start" x="475.5" y="-408.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ CanConvertFrom()</text>
+<text text-anchor="start" x="475.5" y="-397.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ HashBytes()</text>
+</a>
+</g>
+</g>
+<!-- Node9->Node13 -->
+<g id="edge12" class="edge">
+<title>Node9->Node13</title>
+<path fill="none" stroke="#191970" d="M466.5543,-887.021C479.6465,-852.0994 492.2936,-813.5432 500.5,-777 515.0764,-712.0911 521.2847,-637.3152 523.8704,-579.6833"/>
+<polygon fill="none" stroke="#191970" points="463.1305,-886.1784 462.8532,-896.7696 469.6748,-888.663 463.1305,-886.1784"/>
</g>
<!-- Node10 -->
<g id="node7" class="node">
<title>Node10</title>
<g id="a_node7"><a xlink:href="classtvm_1_1runtime_1_1ObjectPtr.html" target="_top" xlink:title="{tvm::runtime::ObjectPtr\l\< tvm::runtime::Object \>\n||+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ObjectPtr()\l+ ~ObjectPtr()\l+ swap()\l+ get()\l+ operator-\>()\land 11 more...\l}">
-<polygon fill="#ffffff" stroke="#000000" points="312.5,-1271.5 312.5,-1449.5 452.5,-1449.5 452.5,-1271.5 312.5,-1271.5"/>
-<text text-anchor="start" x="320.5" y="-1437.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
-<text text-anchor="middle" x="382.5" y="-1426.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
-<polyline fill="none" stroke="#000000" points="312.5,-1419.5 452.5,-1419.5 "/>
-<text text-anchor="middle" x="382.5" y="-1407.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="312.5,-1400.5 452.5,-1400.5 "/>
-<text text-anchor="start" x="320.5" y="-1388.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1377.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1366.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
-<text text-anchor="start" x="320.5" y="-1311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
-<text text-anchor="start" x="320.5" y="-1300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
-<text text-anchor="start" x="320.5" y="-1289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
-<text text-anchor="start" x="320.5" y="-1278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
+<polygon fill="#ffffff" stroke="#000000" points="344.5,-1249.5 344.5,-1427.5 484.5,-1427.5 484.5,-1249.5 344.5,-1249.5"/>
+<text text-anchor="start" x="352.5" y="-1415.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::ObjectPtr</text>
+<text text-anchor="middle" x="414.5" y="-1404.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">< tvm::runtime::Object ></text>
+<polyline fill="none" stroke="#000000" points="344.5,-1397.5 484.5,-1397.5 "/>
+<text text-anchor="middle" x="414.5" y="-1385.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="344.5,-1378.5 484.5,-1378.5 "/>
+<text text-anchor="start" x="352.5" y="-1366.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1355.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1344.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1333.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1322.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1311.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1300.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ~ObjectPtr()</text>
+<text text-anchor="start" x="352.5" y="-1289.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ swap()</text>
+<text text-anchor="start" x="352.5" y="-1278.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ get()</text>
+<text text-anchor="start" x="352.5" y="-1267.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ operator->()</text>
+<text text-anchor="start" x="352.5" y="-1256.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 11 more...</text>
</a>
</g>
</g>
<!-- Node10->Node9 -->
<g id="edge7" class="edge">
<title>Node10->Node9</title>
-<path fill="none" stroke="#404040" d="M382.5,-1271.4973C382.5,-1235.1115 382.5,-1192.409 382.5,-1153.1129"/>
-<polygon fill="none" stroke="#404040" points="382.5001,-1153.0376 378.5,-1147.0377 382.5,-1141.0376 386.5,-1147.0376 382.5001,-1153.0376"/>
-<text text-anchor="middle" x="402" y="-1245" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
+<path fill="none" stroke="#404040" d="M414.5,-1249.4973C414.5,-1213.1115 414.5,-1170.409 414.5,-1131.1129"/>
+<polygon fill="none" stroke="#404040" points="414.5001,-1131.0376 410.5,-1125.0377 414.5,-1119.0376 418.5,-1125.0376 414.5001,-1131.0376"/>
+<text text-anchor="middle" x="434" y="-1223" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> #data_</text>
</g>
<!-- Node11 -->
<g id="node8" class="node">
<title>Node11</title>
<g id="a_node8"><a xlink:href="classtvm_1_1PrimExpr.html" target="_top" xlink:title="Reference to PrimExprNode. ">
-<polygon fill="#ffffff" stroke="#000000" points="337.5,-226.5 337.5,-327.5 491.5,-327.5 491.5,-226.5 337.5,-226.5"/>
-<text text-anchor="middle" x="414.5" y="-315.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::PrimExpr</text>
-<polyline fill="none" stroke="#000000" points="337.5,-308.5 491.5,-308.5 "/>
-<text text-anchor="middle" x="414.5" y="-296.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="337.5,-289.5 491.5,-289.5 "/>
-<text text-anchor="start" x="345.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrimExpr()</text>
-<text text-anchor="start" x="345.5" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrimExpr()</text>
-<text text-anchor="start" x="345.5" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dtype()</text>
-<text text-anchor="start" x="345.5" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
-<text text-anchor="start" x="345.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
+<polygon fill="#ffffff" stroke="#000000" points="337.5,-193.5 337.5,-294.5 491.5,-294.5 491.5,-193.5 337.5,-193.5"/>
+<text text-anchor="middle" x="414.5" y="-282.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::PrimExpr</text>
+<polyline fill="none" stroke="#000000" points="337.5,-275.5 491.5,-275.5 "/>
+<text text-anchor="middle" x="414.5" y="-263.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="337.5,-256.5 491.5,-256.5 "/>
+<text text-anchor="start" x="345.5" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrimExpr()</text>
+<text text-anchor="start" x="345.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ PrimExpr()</text>
+<text text-anchor="start" x="345.5" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ dtype()</text>
+<text text-anchor="start" x="345.5" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ TVM_DEFINE_OBJECT_REF</text>
+<text text-anchor="start" x="345.5" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">_METHODS()</text>
</a>
</g>
</g>
<!-- Node11->Node4 -->
<g id="edge8" class="edge">
<title>Node11->Node4</title>
-<path fill="none" stroke="#404040" d="M385.9987,-226.2812C367.0437,-192.5502 342.038,-148.0519 321.9651,-112.3317"/>
-<polygon fill="none" stroke="#404040" points="321.7849,-112.0109 315.3584,-108.7398 315.9062,-101.5495 322.3327,-104.8206 321.7849,-112.0109"/>
-<text text-anchor="middle" x="360" y="-123" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +channels</text>
+<path fill="none" stroke="#404040" d="M414.5,-193.2859C414.5,-159.0318 414.5,-114.1615 414.5,-80.8604"/>
+<polygon fill="none" stroke="#404040" points="414.5001,-80.7101 410.5,-74.7101 414.5,-68.7101 418.5,-74.7101 414.5001,-80.7101"/>
+<text text-anchor="middle" x="442" y="-90" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +channels</text>
</g>
<!-- Node12->Node11 -->
<g id="edge9" class="edge">
<title>Node12->Node11</title>
-<path fill="none" stroke="#191970" d="M407.3261,-664.8392C408.8258,-583.7614 411.9866,-412.8794 413.5638,-327.6157"/>
-<polygon fill="none" stroke="#191970" points="403.8201,-665.1379 407.1344,-675.2009 410.8189,-665.2674 403.8201,-665.1379"/>
-</g>
-<!-- Node13 -->
-<g id="node10" class="node">
-<title>Node13</title>
-<g id="a_node10"><a xlink:href="classtvm_1_1runtime_1_1DataType.html" target="_top" xlink:title="Runtime primitive data type. ">
-<polygon fill="#ffffff" stroke="#000000" points="509.5,-149.5 509.5,-404.5 641.5,-404.5 641.5,-149.5 509.5,-149.5"/>
-<text text-anchor="middle" x="575.5" y="-392.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::DataType</text>
-<polyline fill="none" stroke="#000000" points="509.5,-385.5 641.5,-385.5 "/>
-<text text-anchor="middle" x="575.5" y="-373.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
-<polyline fill="none" stroke="#000000" points="509.5,-366.5 641.5,-366.5 "/>
-<text text-anchor="start" x="517.5" y="-354.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
-<text text-anchor="start" x="517.5" y="-343.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
-<text text-anchor="start" x="517.5" y="-332.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
-<text text-anchor="start" x="517.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ code()</text>
-<text text-anchor="start" x="517.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ bits()</text>
-<text text-anchor="start" x="517.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ bytes()</text>
-<text text-anchor="start" x="517.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ lanes()</text>
-<text text-anchor="start" x="517.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_scalar()</text>
-<text text-anchor="start" x="517.5" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_bool()</text>
-<text text-anchor="start" x="517.5" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_float()</text>
-<text text-anchor="start" x="517.5" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 14 more...</text>
-<text text-anchor="start" x="517.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Int()</text>
-<text text-anchor="start" x="517.5" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ UInt()</text>
-<text text-anchor="start" x="517.5" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Float()</text>
-<text text-anchor="start" x="517.5" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ BFloat()</text>
-<text text-anchor="start" x="517.5" y="-189.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Bool()</text>
-<text text-anchor="start" x="517.5" y="-178.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Handle()</text>
-<text text-anchor="start" x="517.5" y="-167.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Void()</text>
-<text text-anchor="start" x="517.5" y="-156.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ShapeIndex()</text>
-</a>
-</g>
+<path fill="none" stroke="#191970" d="M414.5,-643.3495C414.5,-560.5508 414.5,-382.4264 414.5,-294.7974"/>
+<polygon fill="none" stroke="#191970" points="411.0001,-643.4357 414.5,-653.4357 418.0001,-643.4357 411.0001,-643.4357"/>
</g>
<!-- Node13->Node4 -->
<g id="edge11" class="edge">
<title>Node13->Node4</title>
-<path fill="none" stroke="#404040" d="M509.3956,-157.732C506.5198,-154.6872 503.5543,-151.7665 500.5,-149 465.7535,-117.5274 419.1598,-94.5379 378.4115,-78.7687"/>
-<polygon fill="none" stroke="#404040" points="378.3204,-78.7345 371.2965,-80.367 367.088,-74.5113 374.1119,-72.8788 378.3204,-78.7345"/>
-<text text-anchor="middle" x="506" y="-123" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +out_dtype</text>
+<path fill="none" stroke="#404040" d="M526.2155,-390.296C525.6473,-297.5669 521.0725,-163.5056 500.5,-116 494.1815,-101.4094 483.8381,-88.1996 472.4765,-76.8669"/>
+<polygon fill="none" stroke="#404040" points="472.3904,-76.7861 465.2779,-75.5975 463.6395,-68.5749 470.752,-69.7636 472.3904,-76.7861"/>
+<text text-anchor="middle" x="563.5" y="-252.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +data_layout</text>
+<text text-anchor="middle" x="563.5" y="-241.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+kernel_layout</text>
+<text text-anchor="middle" x="563.5" y="-230.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+out_layout</text>
+</g>
+<!-- Node14 -->
+<g id="node11" class="node">
+<title>Node14</title>
+<g id="a_node11"><a xlink:href="classtvm_1_1runtime_1_1DataType.html" target="_top" xlink:title="Runtime primitive data type. ">
+<polygon fill="#ffffff" stroke="#000000" points="621.5,-116.5 621.5,-371.5 753.5,-371.5 753.5,-116.5 621.5,-116.5"/>
+<text text-anchor="middle" x="687.5" y="-359.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">tvm::runtime::DataType</text>
+<polyline fill="none" stroke="#000000" points="621.5,-352.5 753.5,-352.5 "/>
+<text text-anchor="middle" x="687.5" y="-340.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> </text>
+<polyline fill="none" stroke="#000000" points="621.5,-333.5 753.5,-333.5 "/>
+<text text-anchor="start" x="629.5" y="-321.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
+<text text-anchor="start" x="629.5" y="-310.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
+<text text-anchor="start" x="629.5" y="-299.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ DataType()</text>
+<text text-anchor="start" x="629.5" y="-288.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ code()</text>
+<text text-anchor="start" x="629.5" y="-277.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ bits()</text>
+<text text-anchor="start" x="629.5" y="-266.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ bytes()</text>
+<text text-anchor="start" x="629.5" y="-255.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ lanes()</text>
+<text text-anchor="start" x="629.5" y="-244.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_scalar()</text>
+<text text-anchor="start" x="629.5" y="-233.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_bool()</text>
+<text text-anchor="start" x="629.5" y="-222.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ is_float()</text>
+<text text-anchor="start" x="629.5" y="-211.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">and 14 more...</text>
+<text text-anchor="start" x="629.5" y="-200.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Int()</text>
+<text text-anchor="start" x="629.5" y="-189.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ UInt()</text>
+<text text-anchor="start" x="629.5" y="-178.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Float()</text>
+<text text-anchor="start" x="629.5" y="-167.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ BFloat()</text>
+<text text-anchor="start" x="629.5" y="-156.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Bool()</text>
+<text text-anchor="start" x="629.5" y="-145.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Handle()</text>
+<text text-anchor="start" x="629.5" y="-134.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ Void()</text>
+<text text-anchor="start" x="629.5" y="-123.5" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000">+ ShapeIndex()</text>
+</a>
+</g>
+</g>
+<!-- Node14->Node4 -->
+<g id="edge13" class="edge">
+<title>Node14->Node4</title>
+<path fill="none" stroke="#404040" d="M621.4709,-129.5965C617.0152,-124.7686 612.356,-120.2001 607.5,-116 578.4592,-90.8817 540.5502,-72.6205 506.0252,-59.8324"/>
+<polygon fill="none" stroke="#404040" points="505.7651,-59.7396 498.7692,-61.4885 494.4642,-55.7034 501.46,-53.9545 505.7651,-59.7396"/>
+<text text-anchor="middle" x="610" y="-90" font-family="Helvetica,sans-Serif" font-size="10.00" fill="#000000"> +out_dtype</text>
</g>
</g>
</svg>
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 787c70f76..6846de997 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1715,7 +1715,7 @@ 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">
@@ -1752,7 +1752,7 @@ 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 fb41b779b..0986b099d 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/4a769c1da/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 0b27fc705..e71df838a 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/4a769c1da/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 a7de472a7..14bb750b6 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/4a769c1da/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 cfd34597e..087e89fc6 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/4a769c1da/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 d649cf8b1..78e5151c0 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/4a769c1da/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 84a4c129c..7dbf4b31f 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/4a769c1da/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 eae7e86c9..8b39b2155 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/4a769c1da/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 e8ece5c29..5cde47820 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/4a769c1da/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 7ccbf8166..80e231b76 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/4a769c1da/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 4157d464a..5ab4a2a2c 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/4a769c1da/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 c3095074b..d5d5de65b 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/4a769c1da/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 f8bbc90c1..fd9996994 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/4a769c1da/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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 b5db983a2..b8e8edfba 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/4a769c1da/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/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/4a769c1da/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/aaee8aa44/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
... 1709 lines suppressed ...