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 2022/05/02 18:53:43 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@9284d32e3af41f33f2798e862ff3ab5e374c141d)
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 da6850fbe deploying docs (apache/tvm@9284d32e3af41f33f2798e862ff3ab5e374c141d)
da6850fbe is described below
commit da6850fbe3725e9ffbee4beeb7073c7b4e249713
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon May 2 18:53:38 2022 +0000
deploying docs (apache/tvm@9284d32e3af41f33f2798e862ff3ab5e374c141d)
---
.../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 +-
docs/_sources/how_to/deploy/tensorrt.rst.txt | 4 +
.../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 | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 2446 +++++++-------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 179 +-
.../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 | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 76 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
docs/how_to/deploy/tensorrt.html | 92 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 18 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2446 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 179 +-
.../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/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 | 5 +-
docs/tutorial/autotvm_relay_x86.html | 161 +-
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 | 41 +-
117 files changed, 2801 insertions(+), 4067 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index ccf84c9f0..725c3d49c 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.zip8dd93f21-001e-497e-925f-3f0ba9071f69 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip66d78ef5-0ace-4c0f-9367-d8386f19f073 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 a73c0b654..504f8e3b0 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<08:44, 83.0kB/s]
0%| | 48.0k/41.5M [00:00<05:32, 131kB/s]
0%| | 96.0k/41.5M [00:00<03:56, 183kB/s]
0%| | 168k/41.5M [00:00<02:49, 256kB/s]
1%| | 344k/41.5M [00:01<01:28, 486kB/s]
1%|1 | 544k/41.5M [00:01<01:04, 664kB/s]
3%|2 | 1.06M/41.5M [00:01<00:31, 1.35MB/s]
5%|5 | 2.13M/41.5M [00:01<00:15, 2.68MB/s]
9%|8 | 3.61M/41.5M [00:01<00:09, 4.24MB/s]
12%|#2 | 5.08M/41.5M [00:02<00:07, 5.27MB/s]
16%|#5 | 6.55M/41.5M [00:02<00:06, 5.96MB/s]
19%|#9 | 8.03M/41.5M [00:02<00:05, 6.38MB/s]
23%|##2 | 9.50M/41.5M [00:02<00:05, 6.69MB/s]
26%|##6 | 11.0M/41.5M [00:02<00:04, 7.00MB/s]
30%|### | 12.5M/41.5M [00:03<00:04, 7.20MB/s]
34%|###3 | 13.9M/41.5M [00:03<00:03, 7.34MB/s]
37%|###7 | 15.4M/41.5M [00:03<00
:03, 7.42MB/s]
41%|#### | 16.9M/41.5M [00:03<00:03, 7.45MB/s]
44%|####4 | 18.3M/41.5M [00:03<00:02, 8.69MB/s]
46%|####6 | 19.2M/41.5M [00:03<00:02, 8.74MB/s]
49%|####8 | 20.1M/41.5M [00:04<00:03, 7.24MB/s]
51%|#####1 | 21.3M/41.5M [00:04<00:02, 7.82MB/s]
54%|#####3 | 22.4M/41.5M [00:04<00:02, 8.38MB/s]
56%|#####5 | 23.2M/41.5M [00:04<00:02, 7.16MB/s]
58%|#####8 | 24.2M/41.5M [00:04<00:02, 7.61MB/s]
61%|######1 | 25.3M/41.5M [00:04<00:02, 8.29MB/s]
63%|######3 | 26.2M/41.5M [00:04<00:02, 6.99MB/s]
65%|######5 | 27.2M/41.5M [00:05<00:02, 6.95MB/s]
69%|######8 | 28.6M/41.5M [00:05<00:01, 8.57MB/s]
71%|#######1 | 29.5M/41.5M [00:05<00:01, 7.90MB/s]
73%|#######2 | 30.3M/41.5M [00:05<00:01, 6.54MB/s]
76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.63MB/s]
80%|#######9 | 33.1M/41.5M [00:05<00:01, 7.08MB/s]
83%|########3 | 34.5M/41.5M [00:06<00:00, 7.54MB/s]
87%|####
####6 | 36.0M/41.5M [00:06<00:00, 7.81MB/s]
90%|######### | 37.5M/41.5M [00:06<00:00, 7.93MB/s]
94%|#########3| 38.9M/41.5M [00:06<00:00, 9.01MB/s]
96%|#########6| 40.0M/41.5M [00:06<00:00, 9.52MB/s]
99%|#########8| 41.0M/41.5M [00:06<00:00, 8.23MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.34MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:05, 89.6kB/s]
0%| | 48.0k/41.5M [00:00<05:06, 142kB/s]
0%| | 96.0k/41.5M [00:00<03:37, 199kB/s]
0%| | 168k/41.5M [00:00<02:35, 278kB/s]
1%| | 296k/41.5M [00:00<01:39, 435kB/s]
1%|1 | 496k/41.5M [00:01<01:04, 665kB/s]
2%|2 | 0.98M/41.5M [00:01<00:30, 1.37MB/s]
4%|3 | 1.66M/41.5M [00:01<00:19, 2.15MB/s]
8%|7 | 3.13M/41.5M [00:01<00:09, 4.10MB/s]
11%|#1 | 4.60M/41.5M [00:01<00:07, 5.40MB/s]
15%|#4 | 6.08M/41.5M [00:02<00:05, 6.32MB/s]
18%|#8 | 7.55M/41.5M [00:02<00:05, 6.94MB/s]
22%|##1 | 9.02M/41.5M [00:02<00:04, 7.36MB/s]
25%|##5 | 10.5M/41.5M [00:02<00:04, 7.62MB/s]
29%|##8 | 11.9M/41.5M [00:02<00:03, 7.81MB/s]
32%|###2 | 13.4M/41.5M [00:02<00:03, 7.93MB/s]
36%|###5 | 14.9M/41.5M [00:03<00
:03, 8.07MB/s]
39%|###9 | 16.3M/41.5M [00:03<00:03, 8.17MB/s]
43%|####2 | 17.8M/41.5M [00:03<00:03, 8.24MB/s]
47%|####6 | 19.3M/41.5M [00:03<00:02, 8.27MB/s]
50%|##### | 20.8M/41.5M [00:03<00:02, 8.32MB/s]
54%|#####3 | 22.3M/41.5M [00:04<00:02, 8.34MB/s]
57%|#####7 | 23.7M/41.5M [00:04<00:02, 8.32MB/s]
61%|###### | 25.2M/41.5M [00:04<00:02, 8.31MB/s]
64%|######4 | 26.7M/41.5M [00:04<00:01, 8.31MB/s]
68%|######7 | 28.1M/41.5M [00:04<00:01, 8.32MB/s]
71%|#######1 | 29.6M/41.5M [00:04<00:01, 8.31MB/s]
75%|#######4 | 31.1M/41.5M [00:05<00:01, 8.27MB/s]
78%|#######8 | 32.5M/41.5M [00:05<00:01, 8.23MB/s]
82%|########2 | 34.0M/41.5M [00:05<00:00, 8.22MB/s]
86%|########5 | 35.5M/41.5M [00:05<00:00, 8.21MB/s]
89%|########9 | 37.0M/41.5M [00:05<00:00, 8.18MB/s]
93%|#########2| 38.4M/41.5M [00:06<00:00, 8.19MB/s]
96%|#########6| 39.9M/41.5M [00:06<00:00, 8.21MB/s]
100%|####
#####9| 41.4M/41.5M [00:06<00:00, 8.23MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.69MB/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 b6a08bd9c..13337ab14 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.198 seconds)
+ **Total running time of the script:** ( 1 minutes 5.108 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 00ade84e8..dee972e14 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]
44%|####3 | 19.4M/44.7M [00:00<00:00, 204MB/s]
94%|#########3| 41.8M/44.7M [00:00<00:00, 222MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
20%|#9 | 8.71M/44.7M [00:00<00:00, 91.3MB/s]
78%|#######8 | 35.0M/44.7M [00:00<00:00, 200MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 198MB/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 2ce5a0e21..6e5b293d7 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.294 seconds)
+ **Total running time of the script:** ( 1 minutes 4.509 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 36ca0e4e4..7a7e52949 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
=================
-**05:19.706** total execution time for **how_to_compile_models** files:
+**05:18.823** total execution time for **how_to_compile_models** files:
-- **01:05.198**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:04.294**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:57.800**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:30.820**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:25.493**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.050**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:20.927**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.090**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:12.269**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.766**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:05.108**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:04.509**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:55.313**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:30.140**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.171**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:22.279**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:20.822**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:19.434**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.501**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.544**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy/tensorrt.rst.txt b/docs/_sources/how_to/deploy/tensorrt.rst.txt
index 7950fcfbd..b91f7b1a8 100644
--- a/docs/_sources/how_to/deploy/tensorrt.rst.txt
+++ b/docs/_sources/how_to/deploy/tensorrt.rst.txt
@@ -193,6 +193,8 @@ Operator support
+------------------------+------------------------------------+
| nn.softmax | |
+------------------------+------------------------------------+
+| nn.conv1d | |
++------------------------+------------------------------------+
| nn.conv2d | |
+------------------------+------------------------------------+
| nn.dense | |
@@ -279,6 +281,8 @@ Operator support
+------------------------+------------------------------------+
| floor | Requires TensorRT 5.1.5 or greater |
+------------------------+------------------------------------+
+| split | Requires TensorRT 5.1.5 or greater |
++------------------------+------------------------------------+
| strided_slice | Requires TensorRT 5.1.5 or greater |
+------------------------+------------------------------------+
| nn.conv3d | Requires TensorRT 6.0.1 or greater |
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 c8d119064..85ae789fe 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2132 16.0434 17.1188 15.8428 0.4144
+ 16.7103 16.7149 16.9045 16.5120 0.1193
diff --git a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
index 51d8d25eb..e4c61f4b8 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]
11%|# | 18.1M/170M [00:00<00:00, 190MB/s]
25%|##5 | 42.9M/170M [00:00<00:00, 230MB/s]
40%|###9 | 67.2M/170M [00:00<00:00, 241MB/s]
53%|#####3 | 90.5M/170M [00:00<00:00, 242MB/s]
67%|######6 | 114M/170M [00:00<00:00, 240MB/s]
82%|########2 | 139M/170M [00:00<00:00, 250MB/s]
97%|#########7| 165M/170M [00:00<00:00, 257MB/s]
100%|##########| 170M/170M [00:00<00:00, 247MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 15.3M/170M [00:00<00:01, 160MB/s]
24%|##4 | 41.1M/170M [00:00<00:00, 225MB/s]
38%|###8 | 65.3M/170M [00:00<00:00, 238MB/s]
53%|#####2 | 89.6M/170M [00:00<00:00, 245MB/s]
68%|######8 | 116M/170M [00:00<00:00, 255MB/s]
84%|########3 | 142M/170M [00:00<00:00, 262MB/s]
99%|#########8| 168M/170M [00:00<00:00, 266MB/s]
100%|##########| 170M/170M [00:00<00:00, 252MB/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').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 5.244 seconds)
+ **Total running time of the script:** ( 3 minutes 4.143 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 b8ce4c587..d61d3b3f4 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]
100%|##########| 13.6M/13.6M [00:00<00:00, 189MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 174MB/s]
@@ -344,7 +344,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4492 90.3375 92.6836 90.1781 0.3620
+ 90.2672 90.2123 92.2220 90.0116 0.2525
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.750 seconds)
+ **Total running time of the script:** ( 1 minutes 4.527 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 2276fd31f..107854310 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
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.9777 120.9738 121.7488 119.9792 0.3577
+ 120.5108 120.5208 121.5700 119.5419 0.3967
@@ -385,7 +385,7 @@ 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 58.427 seconds)
+ **Total running time of the script:** ( 1 minutes 59.237 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 2ff982673..911952956 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.096 seconds)
+ **Total running time of the script:** ( 1 minutes 9.319 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 3e6a919a6..1af4f292f 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%|5 | 7269/132723 [00:00<00:01, 72678.98KB/s]
12%|#2 | 16182/132723 [00:00<00:01, 82352.26KB/s]
19%|#8 | 25041/132723 [00:00<00:01, 85187.07KB/s]
25%|##5 | 33560/132723 [00:00<00:01, 80791.30KB/s]
31%|###1 | 41753/132723 [00:00<00:01, 81183.79KB/s]
38%|###7 | 50160/132723 [00:00<00:01, 81069.31KB/s]
44%|####4 | 59006/132723 [00:00<00:00, 83425.65KB/s]
51%|##### | 67365/132723 [00:00<00:00, 73499.84KB/s]
56%|#####6 | 74919/132723 [00:00<00:00, 69847.87KB/s]
63%|######2 | 83279/132723 [00:01<00:00, 73634.05KB/s]
69%|######9 | 92200/132723 [00:01<00:00, 78032.80KB/s]
76%|#######6 | 101173/132723 [00:01<00:00, 81394.52KB/s]
83%|########2 | 110125/132723 [00:01<00:00, 83757.89KB/s]
89%|########9 | 118593/132723 [00:01<00:00, 83464.86KB/s]
96%|#########6| 127610/132723 [00:01<00:00, 85430.85KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 80756.73KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6325/132723 [00:00<00:01, 63235.13KB/s]
11%|# | 14264/132723 [00:00<00:01, 72733.96KB/s]
17%|#6 | 22053/132723 [00:00<00:01, 75083.59KB/s]
23%|##2 | 29983/132723 [00:00<00:01, 76745.47KB/s]
28%|##8 | 37658/132723 [00:00<00:01, 61122.87KB/s]
34%|###4 | 45566/132723 [00:00<00:01, 66338.69KB/s]
40%|#### | 53538/132723 [00:00<00:01, 70265.27KB/s]
46%|####6 | 61486/132723 [00:00<00:00, 72986.51KB/s]
52%|#####2 | 69404/132723 [00:00<00:00, 74823.58KB/s]
58%|#####8 | 77333/132723 [00:01<00:00, 76151.36KB/s]
64%|######4 | 85245/132723 [00:01<00:00, 77035.35KB/s]
70%|####### | 93157/132723 [00:01<00:00, 77656.33KB/s]
76%|#######6 | 101067/132723 [00:01<00:00, 78084.20KB/s]
82%|########2 | 109019/132723 [00:01<00:00, 78511.24KB/s]
88%|########8 | 116900/132723 [00:01<00:00, 78447.40KB/s]
94%|########
#4| 124846/132723 [00:01<00:00, 78748.20KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74424.05KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 21.940 seconds)
+ **Total running time of the script:** ( 2 minutes 21.137 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 b6de8d38f..c167b1e56 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
=================
-**10:29.026** total execution time for **how_to_deploy_models** files:
+**10:28.254** total execution time for **how_to_deploy_models** files:
-- **03:05.244**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:21.940**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:58.427**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:08.096**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:04.750**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.336**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.046**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.188**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:04.143**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:21.137**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:59.237**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:09.319**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:04.527**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.812**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.890**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.189**: :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 65bfc3c69..f4bcd2ead 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
@@ -423,7 +423,7 @@ 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.zipcb429cc8-3634-46ab-a6cf-8c1f13ccb504 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf374bc1b-4538-4fc6-b9f8-0acef5c381c1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index ea252b48e..0f688d6c8 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
=================
-**00:38.358** total execution time for **how_to_extend_tvm** files:
+**00:37.997** total execution time for **how_to_extend_tvm** files:
-- **00:34.826**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.254**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.066**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.211**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.533**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.233**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.042**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.189**: :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 5008fd28f..af7b52458 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: 5951us [5951us] (45.17%; 45.17%)
- FoldScaleAxis: 7223us [2us] (54.83%; 54.83%)
- FoldConstant: 7221us [1478us] (54.81%; 99.97%)
- InferType: 5742us [5742us] (43.59%; 79.53%)
+ InferType: 5904us [5904us] (45.07%; 45.07%)
+ FoldScaleAxis: 7195us [3us] (54.93%; 54.93%)
+ FoldConstant: 7193us [1488us] (54.91%; 99.96%)
+ InferType: 5705us [5705us] (43.55%; 79.32%)
@@ -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: 5775us [5775us] (44.69%; 44.69%)
- FoldScaleAxis: 7148us [2us] (55.31%; 55.31%)
- FoldConstant: 7146us [1494us] (55.30%; 99.97%)
- InferType: 5652us [5652us] (43.73%; 79.09%)
+ InferType: 5779us [5779us] (44.90%; 44.90%)
+ FoldScaleAxis: 7092us [2us] (55.10%; 55.10%)
+ FoldConstant: 7090us [1477us] (55.09%; 99.97%)
+ InferType: 5613us [5613us] (43.61%; 79.16%)
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 8ff276dc5..7abe2d751 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.112776 ms
+ Convolution: 40.266199 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 a573e514d..6bf137072 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
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.620475 ms
+ conv2d with tensor core: 7.060039 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 0c3c97a13..2223c6667 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018746
- Baseline: 3.440995
+ Numpy running time: 0.017987
+ Baseline: 3.197950
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.295498
+ Opt1: 0.296741
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.333418
+ Opt2: 0.332394
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.116125
+ Opt3: 0.115559
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110524
+ Opt4: 0.110634
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.110295
+ Opt5: 0.110050
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144898
+ Opt6: 0.142357
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 96e0b4966..788a8ffce 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
=================
-**00:35.062** total execution time for **how_to_optimize_operators** files:
+**00:34.007** total execution time for **how_to_optimize_operators** files:
-- **00:32.392**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.422**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.248**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:31.396**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.379**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.232**: :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 6bbbdd96b..70a6ae02d 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
=================
-**05:01.430** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:24.580**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.324**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.309**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:18.986**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.829**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.403**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:01.238** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:16.925**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:20.526**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.173**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:26.196**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.060**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.357**: :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 3b36e204a..b0dd50b06 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
@@ -222,12 +222,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -241,802 +241,465 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((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, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @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) + 8), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtyp [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else(((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) + 12), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @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) + 16), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else(((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) + 20), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @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) + 24), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((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) + 28), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((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) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 188)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((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) + 40), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 308)] = @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) + 44), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((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) + 48), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 364)] = @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) + 52), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((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, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 420)] = @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) + 60), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((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) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else((((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) + 68), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((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) + 76), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @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) + 80), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((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) + 84), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @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) + 88), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 644)] = @tir.if_then_else(((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) + 92), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @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) + 96), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 700)] = @tir.if_then_else(((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) + 100), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else((((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) + 104), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 756)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 580)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((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, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 812)] = @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) + 116), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, d [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((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) + 120), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 868)] = @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) + 124), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, d [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((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) + 128), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 924)] = @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) + 132), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, d [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((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) + 136), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((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) + 140), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 7), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 21), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 35), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 42), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 63), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 70), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 308)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 77), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 20), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 91), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 48)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 832), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1024), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1088), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1216), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1280), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1408), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1472), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1600), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1664), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1792), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1856), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1984), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2048), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2240), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2432), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2624), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2816), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2944), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 3008), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- compute[((blockIdx.x*392) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 196)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 197)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 198)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 199)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 200)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 201)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 202)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
+ }
}
}
@@ -1088,7 +751,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.426 ms
+ Execution time of this operator: 0.361 ms
@@ -1133,36 +796,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1181,14 +844,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1206,10 +869,10 @@ 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__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[384];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1224,750 +887,413 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((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 * 784) + (((((int)threadIdx.x) + 56) / 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) + 84)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 84) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((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 * 784) + (((((int)threadIdx.x) + 112) / 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) + 140)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 140) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((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 * 784) + (((((int)threadIdx.x) + 168) / 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) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 252)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 308)] = (((((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 * 784) + (((((int)threadIdx.x) + 308) / 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) + 336)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 364)] = (((((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 * 784) + (((((int)threadIdx.x) + 364) / 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) + 392)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 420)] = (((((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 * 784) + (((((int)threadIdx.x) + 420) / 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) + 448)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 476)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 476) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 532) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((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 * 784) + (((((int)threadIdx.x) + 560) / 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) + 588)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((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 * 784) + (((((int)threadIdx.x) + 616) / 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) + 644)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 644) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((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 * 784) + (((((int)threadIdx.x) + 672) / 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) + 700)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 700) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 756)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 812)] = (((((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 * 784) + (((((int)threadIdx.x) + 812) / 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) + 840)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 868)] = (((((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 * 784) + (((((int)threadIdx.x) + 868) / 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) + 896)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 924)] = (((((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 * 784) + (((((int)threadIdx.x) + 924) / 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) + 952)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 28) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 28) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 8) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 84) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 36) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 16) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 140) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 44) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 24) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 4) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 12) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 308)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 20) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
- if (((int)threadIdx.x) < 20) {
- kernel_shared[(((int)threadIdx.x) + 364)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 28) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
- compute[((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 196)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 197)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 198)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 199)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 200)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 201)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 202)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
}
@@ -2025,7 +1351,7 @@ 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 24.580 seconds)
+ **Total running time of the script:** ( 2 minutes 16.925 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 8af62c084..0b1bda1b8 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
@@ -614,7 +614,7 @@ 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)
- 9.8081 9.8166 9.8597 9.7480 0.0460
+ 9.9311 9.9254 9.9468 9.9212 0.0112
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 ec1105769..6ca6e90f2 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
@@ -633,7 +633,7 @@ 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)
- 756.7165 755.7170 761.7452 752.6874 3.7648
+ 763.0553 762.3600 769.1978 757.6080 4.7570
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.324 seconds)
+ **Total running time of the script:** ( 1 minutes 20.526 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 1d95d78a7..165d93eaf 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
@@ -362,78 +362,121 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = (nb_j.inner*16)
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ {
+ compute_5: Buffer(compute_4, float32, [64], [])[cse_var_2] = 0f32
+ compute_5[(cse_var_2 + 1)] = 0f32
+ compute_5[(cse_var_2 + 2)] = 0f32
+ compute_5[(cse_var_2 + 3)] = 0f32
+ compute_5[(cse_var_2 + 4)] = 0f32
+ compute_5[(cse_var_2 + 5)] = 0f32
+ compute_5[(cse_var_2 + 6)] = 0f32
+ compute_5[(cse_var_2 + 7)] = 0f32
+ compute_5[(cse_var_2 + 8)] = 0f32
+ compute_5[(cse_var_2 + 9)] = 0f32
+ compute_5[(cse_var_2 + 10)] = 0f32
+ compute_5[(cse_var_2 + 11)] = 0f32
+ compute_5[(cse_var_2 + 12)] = 0f32
+ compute_5[(cse_var_2 + 13)] = 0f32
+ compute_5[(cse_var_2 + 14)] = 0f32
+ compute_5[(cse_var_2 + 15)] = 0f32
+ compute_5[(cse_var_2 + 32)] = 0f32
+ compute_5[(cse_var_2 + 33)] = 0f32
+ compute_5[(cse_var_2 + 34)] = 0f32
+ compute_5[(cse_var_2 + 35)] = 0f32
+ compute_5[(cse_var_2 + 36)] = 0f32
+ compute_5[(cse_var_2 + 37)] = 0f32
+ compute_5[(cse_var_2 + 38)] = 0f32
+ compute_5[(cse_var_2 + 39)] = 0f32
+ compute_5[(cse_var_2 + 40)] = 0f32
+ compute_5[(cse_var_2 + 41)] = 0f32
+ compute_5[(cse_var_2 + 42)] = 0f32
+ compute_5[(cse_var_2 + 43)] = 0f32
+ compute_5[(cse_var_2 + 44)] = 0f32
+ compute_5[(cse_var_2 + 45)] = 0f32
+ compute_5[(cse_var_2 + 46)] = 0f32
+ compute_5[(cse_var_2 + 47)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ let cse_var_35: int32 = (cse_var_2 + 10)
+ let cse_var_34: int32 = (cse_var_2 + 11)
+ let cse_var_33: int32 = (cse_var_2 + 12)
+ let cse_var_32: int32 = (cse_var_2 + 13)
+ let cse_var_31: int32 = (cse_var_2 + 14)
+ let cse_var_30: int32 = (cse_var_2 + 15)
+ let cse_var_29: int32 = (cse_var_2 + 2)
+ let cse_var_28: int32 = (cse_var_2 + 3)
+ let cse_var_27: int32 = (cse_var_2 + 32)
+ let cse_var_26: int32 = (cse_var_2 + 33)
+ let cse_var_25: int32 = (cse_var_2 + 34)
+ let cse_var_24: int32 = (cse_var_2 + 35)
+ let cse_var_23: int32 = (cse_var_2 + 36)
+ let cse_var_22: int32 = (cse_var_2 + 37)
+ let cse_var_21: int32 = (cse_var_2 + 38)
+ let cse_var_20: int32 = (cse_var_2 + 1)
+ let cse_var_19: int32 = (elem_idx*16)
+ let cse_var_18: int32 = (cse_var_2 + 9)
+ let cse_var_17: int32 = (cse_var_2 + 8)
+ let cse_var_16: int32 = (cse_var_2 + 7)
+ let cse_var_15: int32 = (cse_var_2 + 6)
+ let cse_var_14: int32 = (cse_var_2 + 5)
+ let cse_var_13: int32 = (cse_var_2 + 47)
+ let cse_var_12: int32 = (cse_var_2 + 46)
+ let cse_var_11: int32 = (cse_var_2 + 45)
+ let cse_var_10: int32 = (cse_var_2 + 44)
+ let cse_var_9: int32 = (cse_var_2 + 43)
+ let cse_var_8: int32 = (cse_var_2 + 42)
+ let cse_var_7: int32 = (cse_var_2 + 41)
+ let cse_var_6: int32 = (cse_var_2 + 40)
+ let cse_var_5: int32 = (cse_var_2 + 39)
+ let cse_var_4: int32 = (cse_var_2 + 4)
+ let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*512)
{
- compute_5: Buffer(compute_4, float32, [4096], [])[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 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 1)
- let cse_var_16: int32 = (cse_var_18 + 11)
- let cse_var_15: int32 = (cse_var_18 + 12)
- let cse_var_14: int32 = (cse_var_18 + 13)
- let cse_var_13: int32 = (cse_var_18 + 14)
- let cse_var_12: int32 = (cse_var_18 + 15)
- let cse_var_11: int32 = (cse_var_18 + 2)
- let cse_var_10: int32 = (cse_var_18 + 3)
- let cse_var_9: int32 = (cse_var_18 + 4)
- let cse_var_8: int32 = (cse_var_18 + 5)
- let cse_var_7: int32 = (cse_var_18 + 6)
- let cse_var_6: int32 = (cse_var_18 + 7)
- let cse_var_5: int32 = (cse_var_18 + 8)
- let cse_var_4: int32 = (cse_var_18 + 9)
- let cse_var_3: int32 = (cse_var_18 + 10)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_19)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_19)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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))
+ for (i0.inner: int32, 0, 2) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_36: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*1024) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_36] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_36]), 0f32)
+ }
}
}
}
@@ -487,7 +530,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.760 ms
+ Execution time of this operator: 3.021 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 52b17160e..e6e4b7e3a 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
=================
-**00:44.393** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.424** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.515**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.219**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.539**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.231**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.220**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.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_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 b0d438381..dec01e645 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: 65.32/65.32 result: MeasureResult(costs=(0.003544183166666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5835719108581543, timestamp=1651513383.1706367) [('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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.21/110.21 result: MeasureResult(costs=(0.0021005143958333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7704191207885742, timestamp=1651514766.3382714) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.21 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: 0x00007f01a8762fa2
+ 12: 0x00007f4d48ccffa2
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: 144.87/144.87 result: MeasureResult(costs=(0.00159799916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4261679649353027, timestamp=1651513409.5856156) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 144.30/144.30 result: MeasureResult(costs=(0.00160430183,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435715913772583, timestamp=1651514792.7239048) [('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
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.001950
+ Time cost of this operator: 0.002049
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 8f55e72c5..730e9ac4b 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
@@ -292,10 +292,10 @@ 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 312.6 98.712 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.156 0.997 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.291 (1, 1, 10, 10, 3) 1 1
- Total_time - 316.677 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.7 98.753 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.951 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.296 (1, 1, 10, 10, 3) 1 1
+ Total_time - 322.724 - - - -
@@ -357,10 +357,10 @@ 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 136.3 98.072 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 1.25 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.941 0.677 (1, 1, 10, 10, 3) 1 1
- Total_time - 138.979 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 82.65 96.906 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 2.038 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.056 (1, 1, 10, 10, 3) 1 1
+ Total_time - 85.289 - - - -
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 dc2425681..cef5d5275 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
=================
-**00:44.155** total execution time for **how_to_work_with_microtvm** files:
+**00:43.649** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.084**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.474**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.198**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.195**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:39.588**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.453**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.223**: :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``)
+- **00:00.192**: :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 de9e72205..ae2c05772 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
=================
-**00:09.381** total execution time for **how_to_work_with_relay** files:
+**00:09.339** total execution time for **how_to_work_with_relay** files:
-- **00:06.875**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:02.292**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.214**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.509**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.610**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.220**: :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 ebc7c6493..44f44bd4a 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
=================
-**00:05.646** total execution time for **how_to_work_with_schedules** files:
+**00:05.580** total execution time for **how_to_work_with_schedules** files:
-- **00:02.073**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.104**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.723**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.722**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.317**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.249**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.231**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.227**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.046**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.146**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.712**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.693**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.305**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.230**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.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 7e041e8a8..5ead0cc24 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/tmppjo2db3s/input0.cc'\nsource_filename = \"/tmp/tmppjo2db3s/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/tmpu39gg2mj/input0.cc'\nsource_filename = \"/tmp/tmpu39gg2mj/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 8cce16cf3..b6cf41d31 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
=================
-**00:20.353** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.110** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.151**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.203**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:19.916**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.194**: :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 be362781c..19021df7b 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ 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 21.50s!
+ resnet18_v1 inference graph built in 21.43s!
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 e7c10934c..de3ab8322 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 14.93s!
+ yolov3-tiny inference graph built in 14.82s!
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 023206093..3082f9f0d 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
=================
-**01:28.481** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.510** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.847**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.634**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.961**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.549**: :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 0c9b57d6f..86592784e 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
=================
-**00:03.551** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.533** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.993**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.558**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.992**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.541**: :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 fbddab93f..8189c68b6 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
=================
-**00:01.002** total execution time for **topic_vta_tutorials** files:
+**00:01.030** total execution time for **topic_vta_tutorials** files:
-- **00:00.508**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.494**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.524**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.506**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 3025a249c..ae95f8faa 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -185,7 +185,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- .T
+
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.720 ms
+ Execution time of this operator: 94.739 ms
@@ -415,11 +415,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 4.119 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 e6581a5cf..caa5c3be7 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 494.98025591999976, 'median': 494.88435664999884, 'std': 0.727425526710053}
+ {'mean': 492.89957278999964, 'median': 492.98204495000846, 'std': 1.4323416597740124}
@@ -482,31 +482,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 11.11/ 23.95 GFLOPS | Progress: (4/10) | 6.42 s
[Task 1/25] Current/Best: 19.35/ 23.95 GFLOPS | Progress: (8/10) | 10.00 s
[Task 1/25] Current/Best: 16.66/ 23.95 GFLOPS | Progress: (10/10) | 10.99 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 17.00/ 17.00 GFLOPS | Progress: (4/10) | 2.70 s
[Task 2/25] Current/Best: 15.95/ 20.27 GFLOPS | Progress: (8/10) | 3.71 s
[Task 2/25] Current/Best: 8.95/ 20.27 GFLOPS | Progress: (10/10) | 4.95 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 17.33/ 21.31 GFLOPS | Progress: (4/10) | 3.26 s
[Task 3/25] Current/Best: 12.50/ 21.31 GFLOPS | Progress: (8/10) | 5.17 s
[Task 3/25] Current/Best: 11.37/ 21.31 GFLOPS | Progress: (10/10) | 7.18 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 17.40/ 17.40 GFLOPS | Progress: (4/10) | 2.74 s
[Task 4/25] Current/Best: 12.96/ 17.50 GFLOPS | Progress: (8/10) | 5.20 s
[Task 4/25] Current/Best: 12.62/ 17.50 GFLOPS | Progress: (10/10) | 9.05 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 14.17/ 14.17 GFLOPS | Progress: (4/10) | 3.07 s
[Task 5/25] Current/Best: 6.44/ 20.35 GFLOPS | Progress: (8/10) | 5.04 s
[Task 5/25] Current/Best: 15.62/ 20.35 GFLOPS | Progress: (10/10) | 5.72 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 6.62/ 12.31 GFLOPS | Progress: (4/10) | 3.55 s
[Task 6/25] Current/Best: 4.80/ 19.43 GFLOPS | Progress: (8/10) | 6.08 s
[Task 6/25] Current/Best: 8.20/ 23.61 GFLOPS | Progress: (10/10) | 8.26 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 11.18/ 19.69 GFLOPS | Progress: (4/10) | 2.83 s
[Task 7/25] Current/Best: 16.16/ 19.69 GFLOPS | Progress: (8/10) | 5.37 s
[Task 7/25] Current/Best: 11.99/ 19.69 GFLOPS | Progress: (10/10) | 6.85 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 19.11/ 21.78 GFLOPS | Progress: (4/10) | 3.62 s
[Task 8/25] Current/Best: 4.78/ 21.78 GFLOPS | Progress: (8/10) | 11.13 s
[Task 8/25] Current/Best: 13.32/ 21.78 GFLOPS | Progress: (10/10) | 12.10 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 14.19/ 14.19 GFLOPS | Progress: (4/10) | 8.36 s
[Task 9/25] Current/Best: 9.91/ 15.25 GFLOPS | Progress: (8/10) | 10.91 s
[Task 9/25] Current/Best: 11.41/ 15.25 GFLOPS | Progress: (10/10) | 14.10 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 6.73/ 18.39 GFLOPS | Progress: (4/10) | 2.49 s
[Task 10/25] Current/Best: 15.77/ 18.39 GFLOPS | Progress: (8/10) | 3.86 s
[Task 10/25] Current/Best: 16.61/ 18.39 GFLOPS | Progress: (10/10) | 6.14 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 17.72/ 23.40 GFLOPS | Progress: (4/10) | 2.99 s
[Task 11/25] Current/Best: 22.46/ 23.40 GFLOPS | Progress: (8/10) | 5.24 s
[Task 11/25] Current/Best: 23.94/ 23.94 GFLOPS | Progress: (10/10) | 6.25 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 3.63/ 17.06 GFLOPS | Progress: (4/10) | 3.49 s
[Task 12/25] Current/Best: 3.92/ 17.06 GFLOPS | Progress: (8/10) | 5.94 s
[Task 12/25] Current/Best: 14.95/ 17.06 GFLOPS | Progress: (10/10) | 7.16 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 17.87/ 17.87 GFLOPS | Progress: (4/10) | 4.60 s
[Task 13/25] Current/Best: 17.60/ 23.87 GFLOPS | Progress: (8/10) | 7.32 s
[Task 13/25] Current/Best: 12.30/ 23.87 GFLOPS | Progress: (10/10) | 8.54 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 14.01/ 16.05 GFLOPS | Progress: (4/10) | 6.34 s
[Task 14/25] Current/Best: 14.48/ 19.57 GFLOPS | Progress: (8/10) | 8.31 s
[Task 14/25] Current/Best: 4.50/ 19.57 GFLOPS | Progress: (10/10) | 11.80 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 17.85/ 18.38 GFLOPS | Progress: (4/10) | 2.19 s
[Task 15/25] Current/Best: 16.63/ 18.38 GFLOPS | Progress: (8/10) | 3.64 s
[Task 15/25] Current/Best: 20.56/ 20.56 GFLOPS | Progress: (10/10) | 4.68 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 10.68/ 17.74 GFLOPS | Progress: (4/10) | 2.34 s
[Task 16/25] Current/Best: 5.08/ 19.47 GFLOPS | Progress: (8/10) | 3.83 s
[Task 16/25] Current/Best: 4.21/ 19.47 GFLOPS | Progress: (10/10) | 4.64 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 10.57/ 16.93 GFLOPS | Progress: (4/10) | 4.26 s
[Task 17/25] Current/Best: 21.00/ 21.00 GFLOPS | Progress: (8/10) | 6.57 s
[Task 17/25] Current/Best: 15.32/ 21.00 GFLOPS | Progress: (10/10) | 7.44 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 10.83/ 18.19 GFLOPS | Progress: (4/10) | 3.50 s
[Task 18/25] Current/Best: 11.09/ 21.79 GFLOPS | Progress: (8/10) | 9.94 s
[Task 18/25] Current/Best: 13.90/ 21.79 GFLOPS | Progress: (10/10) | 11.17 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 19.68/ 22.88 GFLOPS | Progress: (4/10) | 3.81 s
[Task 19/25] Current/Best: 13.12/ 22.88 GFLOPS | Progress: (8/10) | 10.68 s
[Task 19/25] Current/Best: 9.45/ 22.88 GFLOPS | Progress: (10/10) | 12.35 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 13.57/ 15.81 GFLOPS | Progress: (4/10) | 2.98 s
[Task 20/25] Current/Best: 14.64/ 15.81 GFLOPS | Progress: (8/10) | 5.64 s
[Task 20/25] Current/Best: 22.55/ 22.55 GFLOPS | Progress: (10/10) | 6.70 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 13.14/ 18.52 GFLOPS | Progress: (4/10) | 2.44 s
[Task 21/25] Current/Best: 6.87/ 19.13 GFLOPS | Progress: (8/10) | 3.82 s
[Task 21/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (10/10) | 4.47 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 9.69/ 13.90 GFLOPS | Progress: (4/10) | 6.22 s
[Task 1/25] Current/Best: 10.49/ 16.41 GFLOPS | Progress: (8/10) | 11.53 s
[Task 1/25] Current/Best: 17.45/ 17.45 GFLOPS | Progress: (10/10) | 13.66 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 19.84/ 21.66 GFLOPS | Progress: (4/10) | 1.88 s
[Task 2/25] Current/Best: 16.75/ 21.66 GFLOPS | Progress: (8/10) | 3.18 s
[Task 2/25] Current/Best: 22.07/ 22.07 GFLOPS | Progress: (10/10) | 3.69 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 8.53/ 14.99 GFLOPS | Progress: (4/10) | 4.10 s
[Task 3/25] Current/Best: 14.31/ 20.77 GFLOPS | Progress: (8/10) | 6.22 s
[Task 3/25] Current/Best: 17.53/ 20.77 GFLOPS | Progress: (10/10) | 7.01 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 12.72/ 17.70 GFLOPS | Progress: (4/10) | 2.68 s
[Task 4/25] Current/Best: 14.63/ 17.70 GFLOPS | Progress: (8/10) | 4.54 s
[Task 4/25] Current/Best: 4.05/ 17.70 GFLOPS | Progress: (10/10) | 5.64 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 14.96/ 17.73 GFLOPS | Progress: (4/10) | 2.57 s
[Task 5/25] Current/Best: 3.14/ 18.36 GFLOPS | Progress: (8/10) | 4.51 s
[Task 5/25] Current/Best: 12.83/ 18.36 GFLOPS | Progress: (10/10) | 5.18 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 15.94/ 18.67 GFLOPS | Progress: (4/10) | 3.88 s
[Task 6/25] Current/Best: 7.78/ 18.67 GFLOPS | Progress: (8/10) | 7.19 s
[Task 6/25] Current/Best: 16.04/ 19.86 GFLOPS | Progress: (10/10) | 7.90 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 12.38/ 13.60 GFLOPS | Progress: (4/10) | 3.01 s
[Task 7/25] Current/Best: 21.11/ 23.81 GFLOPS | Progress: (8/10) | 4.42 s
[Task 7/25] Current/Best: 15.50/ 23.81 GFLOPS | Progress: (10/10) | 5.29 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 13.52/ 14.10 GFLOPS | Progress: (4/10) | 6.88 s
[Task 8/25] Current/Best: 11.01/ 14.10 GFLOPS | Progress: (8/10) | 11.73 s
[Task 8/25] Current/Best: 4.40/ 14.10 GFLOPS | Progress: (10/10) | 13.26 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 13.79/ 19.18 GFLOPS | Progress: (4/10) | 2.70 s
[Task 9/25] Current/Best: 11.62/ 21.25 GFLOPS | Progress: (8/10) | 4.32 s
[Task 9/25] Current/Best: 17.72/ 21.25 GFLOPS | Progress: (10/10) | 5.06 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.98/ 16.98 GFLOPS | Progress: (4/10) | 3.48 s
[Task 10/25] Current/Best: 11.04/ 16.98 GFLOPS | Progress: (8/10) | 4.92 s
[Task 10/25] Current/Best: 5.95/ 16.98 GFLOPS | Progress: (10/10) | 5.82 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 17.32/ 21.23 GFLOPS | Progress: (4/10) | 3.13 s
[Task 11/25] Current/Best: 23.59/ 23.59 GFLOPS | Progress: (8/10) | 4.65 s
[Task 11/25] Current/Best: 15.25/ 23.59 GFLOPS | Progress: (10/10) | 6.02 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 14.66/ 18.60 GFLOPS | Progress: (4/10) | 2.87 s
[Task 12/25] Current/Best: 13.05/ 22.09 GFLOPS | Progress: (8/10) | 4.95 s
[Task 12/25] Current/Best: 4.54/ 22.09 GFLOPS | Progress: (10/10) | 6.17 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 3.66/ 12.67 GFLOPS | Progress: (4/10) | 4.26 s
[Task 13/25] Current/Best: 15.97/ 19.44 GFLOPS | Progress: (8/10) | 7.35 s
[Task 13/25] Current/Best: 20.81/ 20.81 GFLOPS | Progress: (10/10) | 9.29 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 12.96/ 12.96 GFLOPS | Progress: (4/10) | 3.43 s
[Task 14/25] Current/Best: 12.92/ 21.64 GFLOPS | Progress: (8/10) | 5.40 s
[Task 14/25] Current/Best: 3.07/ 21.64 GFLOPS | Progress: (10/10) | 7.29 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 11.20/ 20.55 GFLOPS | Progress: (4/10) | 2.48 s
[Task 15/25] Current/Best: 10.98/ 20.89 GFLOPS | Progress: (8/10) | 6.52 s
[Task 15/25] Current/Best: 13.52/ 20.89 GFLOPS | Progress: (10/10) | 7.43 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 14.78/ 18.01 GFLOPS | Progress: (4/10) | 3.61 s
[Task 16/25] Current/Best: 10.09/ 18.51 GFLOPS | Progress: (8/10) | 5.03 s
[Task 16/25] Current/Best: 10.76/ 18.51 GFLOPS | Progress: (10/10) | 7.04 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 5.57/ 19.22 GFLOPS | Progress: (4/10) | 3.43 s
[Task 17/25] Current/Best: 1.56/ 19.22 GFLOPS | Progress: (8/10) | 7.28 s
[Task 17/25] Current/Best: 19.08/ 23.75 GFLOPS | Progress: (10/10) | 7.99 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 15.31/ 18.10 GFLOPS | Progress: (4/10) | 7.74 s
[Task 18/25] Current/Best: 15.27/ 18.10 GFLOPS | Progress: (8/10) | 10.14 s
[Task 18/25] Current/Best: 1.57/ 18.10 GFLOPS | Progress: (10/10) | 12.25 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 6.47/ 20.22 GFLOPS | Progress: (4/10) | 7.88 s
[Task 19/25] Current/Best: 23.00/ 23.00 GFLOPS | Progress: (8/10) | 11.11 s
[Task 19/25] Current/Best: 19.22/ 23.00 GFLOPS | Progress: (10/10) | 12.77 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 7.28/ 18.32 GFLOPS | Progress: (4/10) | 4.06 s
[Task 20/25] Current/Best: 12.69/ 18.32 GFLOPS | Progress: (8/10) | 5.96 s
[Task 20/25] Current/Best: 9.94/ 18.32 GFLOPS | Progress: (10/10) | 6.76 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 1.62/ 14.51 GFLOPS | Progress: (4/10) | 3.47 s
[Task 21/25] Current/Best: 16.53/ 16.87 GFLOPS | Progress: (8/10) | 4.71 s
[Task 21/25] Current/Best: 13.81/ 16.87 GFLOPS | Progress: (10/10) | 5.36 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 22/25] Current/Best: 5.36/ 13.44 GFLOPS | Progress: (4/10) | 5.01 s
[Task 22/25] Current/Best: 6.20/ 14.65 GFLOPS | Progress: (8/10) | 6.66 s
[Task 22/25] Current/Best: 18.65/ 22.11 GFLOPS | Progress: (10/10) | 7.24 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 13.48/ 13.48 GFLOPS | Progress: (4/10) | 6.45 s
[Task 23/25] Current/Best: 19.25/ 23.97 GFLOPS | Progress: (8/10) | 9.53 s
[Task 23/25] Current/Best: 6.66/ 23.97 GFLOPS | Progress: (10/10) | 10.69 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 3.71/ 3.71 GFLOPS | Progress: (4/10) | 18.26 s
[Task 24/25] Current/Best: 3.85/ 10.39 GFLOPS | Progress: (8/10) | 20.04 s
[Task 24/25] Current/Best: 4.34/ 10.39 GFLOPS | Progress: (10/10) | 28.35 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 6.01/ 6.01 GFLOPS | Progress: (4/10) | 2.48 s
[Task 25/25] Current/Best: 8.70/ 8.70 GFLOPS | Progress: (8/10) | 3.48 s
[Task 25/25] Current/Best: 1.55/ 8.70 GFLOPS | Progress: (10/10) | 4.00 s Done.
-
+
[Task 22/25] Current/Best: 5.32/ 18.04 GFLOPS | Progress: (4/10) | 4.10 s
[Task 22/25] Current/Best: 7.92/ 18.04 GFLOPS | Progress: (8/10) | 6.18 s
[Task 22/25] Current/Best: 11.84/ 19.82 GFLOPS | Progress: (10/10) | 7.11 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 10.03/ 11.94 GFLOPS | Progress: (4/10) | 4.26 s
[Task 23/25] Current/Best: 7.98/ 23.27 GFLOPS | Progress: (8/10) | 6.57 s
[Task 23/25] Current/Best: 8.76/ 23.27 GFLOPS | Progress: (10/10) | 7.55 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 4.62/ 10.52 GFLOPS | Progress: (4/10) | 2.06 s
[Task 24/25] Current/Best: 3.67/ 10.52 GFLOPS | Progress: (8/10) | 8.67 s
[Task 24/25] Current/Best: 5.69/ 10.52 GFLOPS | Progress: (10/10) | 9.22 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 25/25] Current/Best: 9.45/ 9.45 GFLOPS | Progress: (4/10) | 2.31 s
[Task 25/25] Current/Best: 1.55/ 9.45 GFLOPS | Progress: (8/10) | 7.53 s
[Task 25/25] Current/Best: 8.06/ 9.45 GFLOPS | Progress: (10/10) | 35.22 s
The output from this tuning process will look something like this:
@@ -648,8 +648,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 439.19951451000316, 'median': 438.8799076499936, 'std': 0.7492071285885055}
- unoptimized: {'mean': 494.98025591999976, 'median': 494.88435664999884, 'std': 0.727425526710053}
+ optimized: {'mean': 431.96885749000785, 'median': 430.77323334999846, 'std': 2.512853857751077}
+ unoptimized: {'mean': 492.89957278999964, 'median': 492.98204495000846, 'std': 1.4323416597740124}
@@ -669,7 +669,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 55.869 seconds)
+ **Total running time of the script:** ( 6 minutes 54.059 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 a01177d45..7b846c8a3 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.233e-07 secs/op
+ 1.28e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index fad415d76..368affbbc 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, 0xd54fb30)), stage(b, placeholder(b, 0x16b58190)), 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, 0x25b62250)), stage(b, placeholder(b, 0x56d8350)), 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 ade84e85a..6c70cc9c5 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
=================
-**09:55.528** total execution time for **tutorial** files:
+**09:25.957** total execution time for **tutorial** files:
-- **06:55.869**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:04.119**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **01:01.105**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:26.064**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:25.975**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:01.339**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.704**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.191**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.044**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.041**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.040**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.038**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **06:54.059**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:58.813**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:38.763**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:26.390**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:25.568**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.254**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.736**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.221**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.041**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.039**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.038**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.034**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index cd9b384ae..5aa23ce1d 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -244,7 +244,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000006
+ naive: 0.000008
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.23588999992353e-06 1.0
- naive 5.8697e-06 0.7126977169503843
- parallel 6.125e-06 0.7436961882755684
- vector 2.5747199999999996e-05 3.1262195100030548
+ numpy 8.37700000147379e-06 1.0
+ naive 7.5882000000000005e-06 0.9058374118019562
+ parallel 6.121600000000001e-06 0.7307628027841722
+ vector 2.56049e-05 3.0565715644616516
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018131
+ Numpy running time: 0.018165
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.437530
+ none: 3.257098
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.297706
+ blocking: 0.295354
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.333837
+ vectorization: 0.341762
@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], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.116652
+ loop permutation: 0.118901
@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], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.108312
+ array packing: 0.110375
@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], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.109991
+ block caching: 0.109977
@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], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.143902
+ parallelization: 0.144555
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4375296301 1.0
- blocking 0.2977060399 0.08660464692237127
- vectorization 0.3338366074 0.09711526686979814
- loop permutation 0.11665160240000001 0.03393471910134679
- array packing 0.10831157900000002 0.031508551388646264
- block caching 0.10999133450000001 0.03199720332208462
- parallelization 0.14390160359999998 0.04186192384785751
+ none 3.2570984926 1.0
+ blocking 0.2953539663 0.0906800844282212
+ vectorization 0.34176224069999994 0.10492843292165414
+ loop permutation 0.1189009955 0.03650518882684647
+ array packing 0.1103748184 0.03388746721990976
+ block caching 0.1099765134 0.03376517893145151
+ parallelization 0.1445548765 0.0443814876425822
@@ -1541,11 +1541,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.105 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 9bb3e64db..a34c6162f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-be90c656e81d1c91672a157c986974166ca64e50
+9284d32e3af41f33f2798e862ff3ab5e374c141d
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 11b1c4e41..82a89b5d7 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.zip8dd93f21-001e-497e-925f-3f0ba9071f69 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.zip66d78ef5-0ace-4c0f-9367-d8386f19f073 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 b9cada129..22c0f83a3 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,46 +406,42 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<08:44, 83.0kB/s]
- 0%| | 48.0k/41.5M [00:00<05:32, 131kB/s]
- 0%| | 96.0k/41.5M [00:00<03:56, 183kB/s]
- 0%| | 168k/41.5M [00:00<02:49, 256kB/s]
- 1%| | 344k/41.5M [00:01<01:28, 486kB/s]
- 1%|1 | 544k/41.5M [00:01<01:04, 664kB/s]
- 3%|2 | 1.06M/41.5M [00:01<00:31, 1.35MB/s]
- 5%|5 | 2.13M/41.5M [00:01<00:15, 2.68MB/s]
- 9%|8 | 3.61M/41.5M [00:01<00:09, 4.24MB/s]
- 12%|#2 | 5.08M/41.5M [00:02<00:07, 5.27MB/s]
- 16%|#5 | 6.55M/41.5M [00:02<00:06, 5.96MB/s]
- 19%|#9 | 8.03M/41.5M [00:02<00:05, 6.38MB/s]
- 23%|##2 | 9.50M/41.5M [00:02<00:05, 6.69MB/s]
- 26%|##6 | 11.0M/41.5M [00:02<00:04, 7.00MB/s]
- 30%|### | 12.5M/41.5M [00:03<00:04, 7.20MB/s]
- 34%|###3 | 13.9M/41.5M [00:03<00:03, 7.34MB/s]
- 37%|###7 | 15.4M/41.5M [00:03<00:03, 7.42MB/s]
- 41%|#### | 16.9M/41.5M [00:03<00:03, 7.45MB/s]
- 44%|####4 | 18.3M/41.5M [00:03<00:02, 8.69MB/s]
- 46%|####6 | 19.2M/41.5M [00:03<00:02, 8.74MB/s]
- 49%|####8 | 20.1M/41.5M [00:04<00:03, 7.24MB/s]
- 51%|#####1 | 21.3M/41.5M [00:04<00:02, 7.82MB/s]
- 54%|#####3 | 22.4M/41.5M [00:04<00:02, 8.38MB/s]
- 56%|#####5 | 23.2M/41.5M [00:04<00:02, 7.16MB/s]
- 58%|#####8 | 24.2M/41.5M [00:04<00:02, 7.61MB/s]
- 61%|######1 | 25.3M/41.5M [00:04<00:02, 8.29MB/s]
- 63%|######3 | 26.2M/41.5M [00:04<00:02, 6.99MB/s]
- 65%|######5 | 27.2M/41.5M [00:05<00:02, 6.95MB/s]
- 69%|######8 | 28.6M/41.5M [00:05<00:01, 8.57MB/s]
- 71%|#######1 | 29.5M/41.5M [00:05<00:01, 7.90MB/s]
- 73%|#######2 | 30.3M/41.5M [00:05<00:01, 6.54MB/s]
- 76%|#######6 | 31.6M/41.5M [00:05<00:01, 6.63MB/s]
- 80%|#######9 | 33.1M/41.5M [00:05<00:01, 7.08MB/s]
- 83%|########3 | 34.5M/41.5M [00:06<00:00, 7.54MB/s]
- 87%|########6 | 36.0M/41.5M [00:06<00:00, 7.81MB/s]
- 90%|######### | 37.5M/41.5M [00:06<00:00, 7.93MB/s]
- 94%|#########3| 38.9M/41.5M [00:06<00:00, 9.01MB/s]
- 96%|#########6| 40.0M/41.5M [00:06<00:00, 9.52MB/s]
- 99%|#########8| 41.0M/41.5M [00:06<00:00, 8.23MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 6.34MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:05, 89.6kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:06, 142kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:37, 199kB/s]
+ 0%| | 168k/41.5M [00:00<02:35, 278kB/s]
+ 1%| | 296k/41.5M [00:00<01:39, 435kB/s]
+ 1%|1 | 496k/41.5M [00:01<01:04, 665kB/s]
+ 2%|2 | 0.98M/41.5M [00:01<00:30, 1.37MB/s]
+ 4%|3 | 1.66M/41.5M [00:01<00:19, 2.15MB/s]
+ 8%|7 | 3.13M/41.5M [00:01<00:09, 4.10MB/s]
+ 11%|#1 | 4.60M/41.5M [00:01<00:07, 5.40MB/s]
+ 15%|#4 | 6.08M/41.5M [00:02<00:05, 6.32MB/s]
+ 18%|#8 | 7.55M/41.5M [00:02<00:05, 6.94MB/s]
+ 22%|##1 | 9.02M/41.5M [00:02<00:04, 7.36MB/s]
+ 25%|##5 | 10.5M/41.5M [00:02<00:04, 7.62MB/s]
+ 29%|##8 | 11.9M/41.5M [00:02<00:03, 7.81MB/s]
+ 32%|###2 | 13.4M/41.5M [00:02<00:03, 7.93MB/s]
+ 36%|###5 | 14.9M/41.5M [00:03<00:03, 8.07MB/s]
+ 39%|###9 | 16.3M/41.5M [00:03<00:03, 8.17MB/s]
+ 43%|####2 | 17.8M/41.5M [00:03<00:03, 8.24MB/s]
+ 47%|####6 | 19.3M/41.5M [00:03<00:02, 8.27MB/s]
+ 50%|##### | 20.8M/41.5M [00:03<00:02, 8.32MB/s]
+ 54%|#####3 | 22.3M/41.5M [00:04<00:02, 8.34MB/s]
+ 57%|#####7 | 23.7M/41.5M [00:04<00:02, 8.32MB/s]
+ 61%|###### | 25.2M/41.5M [00:04<00:02, 8.31MB/s]
+ 64%|######4 | 26.7M/41.5M [00:04<00:01, 8.31MB/s]
+ 68%|######7 | 28.1M/41.5M [00:04<00:01, 8.32MB/s]
+ 71%|#######1 | 29.6M/41.5M [00:04<00:01, 8.31MB/s]
+ 75%|#######4 | 31.1M/41.5M [00:05<00:01, 8.27MB/s]
+ 78%|#######8 | 32.5M/41.5M [00:05<00:01, 8.23MB/s]
+ 82%|########2 | 34.0M/41.5M [00:05<00:00, 8.22MB/s]
+ 86%|########5 | 35.5M/41.5M [00:05<00:00, 8.21MB/s]
+ 89%|########9 | 37.0M/41.5M [00:05<00:00, 8.18MB/s]
+ 93%|#########2| 38.4M/41.5M [00:06<00:00, 8.19MB/s]
+ 96%|#########6| 39.9M/41.5M [00:06<00:00, 8.21MB/s]
+100%|#########9| 41.4M/41.5M [00:06<00:00, 8.23MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 6.69MB/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 3b4bde73a..466699ea9 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ 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 5.198 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.108 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 ff6f385d5..80ef80699 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,9 +387,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 44%|####3 | 19.4M/44.7M [00:00<00:00, 204MB/s]
- 94%|#########3| 41.8M/44.7M [00:00<00:00, 222MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/s]
+ 20%|#9 | 8.71M/44.7M [00:00<00:00, 91.3MB/s]
+ 78%|#######8 | 35.0M/44.7M [00:00<00:00, 200MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 198MB/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 952e6cbad..16bf480df 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,7 @@ 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 4.294 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.509 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 eef687bbb..dd4c9196a 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>05:19.706</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:18.823</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:05.198</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>01:04.294</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>00:57.800</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>00:30.820</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>00:25.493</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>00:21.050</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>00:20.927</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>00:19.090</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>00:12.269</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>00:02.766</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>01:05.108</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>01:04.509</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>00:55.313</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>00:30.140</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>00:25.171</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>00:22.279</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>00:20.822</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>00:19.434</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>00:13.501</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>00:02.544</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/tensorrt.html b/docs/how_to/deploy/tensorrt.html
index 15a465067..52959397b 100644
--- a/docs/how_to/deploy/tensorrt.html
+++ b/docs/how_to/deploy/tensorrt.html
@@ -502,133 +502,139 @@ This will give greater performance, but will consume more memory.</p></li>
<tr class="row-odd"><td><p>nn.softmax</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>nn.conv2d</p></td>
+<tr class="row-even"><td><p>nn.conv1d</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.dense</p></td>
+<tr class="row-odd"><td><p>nn.conv2d</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>nn.bias_add</p></td>
+<tr class="row-even"><td><p>nn.dense</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>add</p></td>
+<tr class="row-odd"><td><p>nn.bias_add</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>subtract</p></td>
+<tr class="row-even"><td><p>add</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>multiply</p></td>
+<tr class="row-odd"><td><p>subtract</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>divide</p></td>
+<tr class="row-even"><td><p>multiply</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>power</p></td>
+<tr class="row-odd"><td><p>divide</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>maximum</p></td>
+<tr class="row-even"><td><p>power</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>minimum</p></td>
+<tr class="row-odd"><td><p>maximum</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>nn.max_pool2d</p></td>
+<tr class="row-even"><td><p>minimum</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.avg_pool2d</p></td>
+<tr class="row-odd"><td><p>nn.max_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>nn.global_max_pool2d</p></td>
+<tr class="row-even"><td><p>nn.avg_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.global_avg_pool2d</p></td>
+<tr class="row-odd"><td><p>nn.global_max_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>exp</p></td>
+<tr class="row-even"><td><p>nn.global_avg_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>log</p></td>
+<tr class="row-odd"><td><p>exp</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>sqrt</p></td>
+<tr class="row-even"><td><p>log</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>abs</p></td>
+<tr class="row-odd"><td><p>sqrt</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>negative</p></td>
+<tr class="row-even"><td><p>abs</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.batch_flatten</p></td>
+<tr class="row-odd"><td><p>negative</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>expand_dims</p></td>
+<tr class="row-even"><td><p>nn.batch_flatten</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>squeeze</p></td>
+<tr class="row-odd"><td><p>expand_dims</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>concatenate</p></td>
+<tr class="row-even"><td><p>squeeze</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.conv2d_transpose</p></td>
+<tr class="row-odd"><td><p>concatenate</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>transpose</p></td>
+<tr class="row-even"><td><p>nn.conv2d_transpose</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>layout_transform</p></td>
+<tr class="row-odd"><td><p>transpose</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>reshape</p></td>
+<tr class="row-even"><td><p>layout_transform</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.pad</p></td>
+<tr class="row-odd"><td><p>reshape</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>sum</p></td>
+<tr class="row-even"><td><p>nn.pad</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>prod</p></td>
+<tr class="row-odd"><td><p>sum</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>max</p></td>
+<tr class="row-even"><td><p>prod</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>min</p></td>
+<tr class="row-odd"><td><p>max</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>mean</p></td>
+<tr class="row-even"><td><p>min</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.adaptive_max_pool2d</p></td>
+<tr class="row-odd"><td><p>mean</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>nn.adaptive_avg_pool2d</p></td>
+<tr class="row-even"><td><p>nn.adaptive_max_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-odd"><td><p>nn.batch_matmul</p></td>
+<tr class="row-odd"><td><p>nn.adaptive_avg_pool2d</p></td>
<td></td>
</tr>
-<tr class="row-even"><td><p>clip</p></td>
+<tr class="row-even"><td><p>nn.batch_matmul</p></td>
+<td></td>
+</tr>
+<tr class="row-odd"><td><p>clip</p></td>
+<td><p>Requires TensorRT 5.1.5 or greater</p></td>
+</tr>
+<tr class="row-even"><td><p>nn.leaky_relu</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-odd"><td><p>nn.leaky_relu</p></td>
+<tr class="row-odd"><td><p>sin</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-even"><td><p>sin</p></td>
+<tr class="row-even"><td><p>cos</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-odd"><td><p>cos</p></td>
+<tr class="row-odd"><td><p>atan</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-even"><td><p>atan</p></td>
+<tr class="row-even"><td><p>ceil</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-odd"><td><p>ceil</p></td>
+<tr class="row-odd"><td><p>floor</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
-<tr class="row-even"><td><p>floor</p></td>
+<tr class="row-even"><td><p>split</p></td>
<td><p>Requires TensorRT 5.1.5 or greater</p></td>
</tr>
<tr class="row-odd"><td><p>strided_slice</p></td>
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 8ee59b968..00e8009c2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.2132 16.0434 17.1188 15.8428 0.4144
+ 16.7103 16.7149 16.9045 16.5120 0.1193
</pre></div>
</div>
</div>
diff --git a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
index 8c897f05e..0723d2297 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,14 +409,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 11%|# | 18.1M/170M [00:00<00:00, 190MB/s]
- 25%|##5 | 42.9M/170M [00:00<00:00, 230MB/s]
- 40%|###9 | 67.2M/170M [00:00<00:00, 241MB/s]
- 53%|#####3 | 90.5M/170M [00:00<00:00, 242MB/s]
- 67%|######6 | 114M/170M [00:00<00:00, 240MB/s]
- 82%|########2 | 139M/170M [00:00<00:00, 250MB/s]
- 97%|#########7| 165M/170M [00:00<00:00, 257MB/s]
-100%|##########| 170M/170M [00:00<00:00, 247MB/s]
+ 9%|9 | 15.3M/170M [00:00<00:01, 160MB/s]
+ 24%|##4 | 41.1M/170M [00:00<00:00, 225MB/s]
+ 38%|###8 | 65.3M/170M [00:00<00:00, 238MB/s]
+ 53%|#####2 | 89.6M/170M [00:00<00:00, 245MB/s]
+ 68%|######8 | 116M/170M [00:00<00:00, 255MB/s]
+ 84%|########3 | 142M/170M [00:00<00:00, 262MB/s]
+ 99%|#########8| 168M/170M [00:00<00:00, 266MB/s]
+100%|##########| 170M/170M [00:00<00:00, 252MB/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').
@@ -509,7 +509,7 @@ 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 5.244 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.143 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 81e8dca1c..a1d3b032d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 189MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 174MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +539,7 @@ 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)
- 90.4492 90.3375 92.6836 90.1781 0.3620
+ 90.2672 90.2123 92.2220 90.0116 0.2525
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +578,7 @@ 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 4.750 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.527 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 71af61afe..8a22487f2 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ 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)
- 120.9777 120.9738 121.7488 119.9792 0.3577
+ 120.5108 120.5208 121.5700 119.5419 0.3967
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ 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 58.427 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 59.237 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 14fc1d094..3a02e30db 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ 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 8.096 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.319 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 5cb6cf67f..4ef04a293 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%|5 | 7269/132723 [00:00<00:01, 72678.98KB/s]
- 12%|#2 | 16182/132723 [00:00<00:01, 82352.26KB/s]
- 19%|#8 | 25041/132723 [00:00<00:01, 85187.07KB/s]
- 25%|##5 | 33560/132723 [00:00<00:01, 80791.30KB/s]
- 31%|###1 | 41753/132723 [00:00<00:01, 81183.79KB/s]
- 38%|###7 | 50160/132723 [00:00<00:01, 81069.31KB/s]
- 44%|####4 | 59006/132723 [00:00<00:00, 83425.65KB/s]
- 51%|##### | 67365/132723 [00:00<00:00, 73499.84KB/s]
- 56%|#####6 | 74919/132723 [00:00<00:00, 69847.87KB/s]
- 63%|######2 | 83279/132723 [00:01<00:00, 73634.05KB/s]
- 69%|######9 | 92200/132723 [00:01<00:00, 78032.80KB/s]
- 76%|#######6 | 101173/132723 [00:01<00:00, 81394.52KB/s]
- 83%|########2 | 110125/132723 [00:01<00:00, 83757.89KB/s]
- 89%|########9 | 118593/132723 [00:01<00:00, 83464.86KB/s]
- 96%|#########6| 127610/132723 [00:01<00:00, 85430.85KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 80756.73KB/s]
+ 5%|4 | 6325/132723 [00:00<00:01, 63235.13KB/s]
+ 11%|# | 14264/132723 [00:00<00:01, 72733.96KB/s]
+ 17%|#6 | 22053/132723 [00:00<00:01, 75083.59KB/s]
+ 23%|##2 | 29983/132723 [00:00<00:01, 76745.47KB/s]
+ 28%|##8 | 37658/132723 [00:00<00:01, 61122.87KB/s]
+ 34%|###4 | 45566/132723 [00:00<00:01, 66338.69KB/s]
+ 40%|#### | 53538/132723 [00:00<00:01, 70265.27KB/s]
+ 46%|####6 | 61486/132723 [00:00<00:00, 72986.51KB/s]
+ 52%|#####2 | 69404/132723 [00:00<00:00, 74823.58KB/s]
+ 58%|#####8 | 77333/132723 [00:01<00:00, 76151.36KB/s]
+ 64%|######4 | 85245/132723 [00:01<00:00, 77035.35KB/s]
+ 70%|####### | 93157/132723 [00:01<00:00, 77656.33KB/s]
+ 76%|#######6 | 101067/132723 [00:01<00:00, 78084.20KB/s]
+ 82%|########2 | 109019/132723 [00:01<00:00, 78511.24KB/s]
+ 88%|########8 | 116900/132723 [00:01<00:00, 78447.40KB/s]
+ 94%|#########4| 124846/132723 [00:01<00:00, 78748.20KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 74424.05KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -470,7 +471,7 @@ 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 21.940 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.137 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 bd23162e1..3c4ce728b 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>10:29.026</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:28.254</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:05.244</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>02:21.940</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>01:58.427</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>01:08.096</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>01:04.750</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>00:28.336</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>00:22.046</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>00:00.188</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>03:04.143</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>02:21.137</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>01:59.237</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>01:09.319</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>01:04.527</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>00:27.812</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>00:21.890</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>00:00.189</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 a4ac5e1fb..4a6da0f87 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ 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.zipcb429cc8-3634-46ab-a6cf-8c1f13ccb504 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.zipf374bc1b-4538-4fc6-b9f8-0acef5c381c1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index cc0e16e7c..31391d8cc 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>00:38.358</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.997</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.826</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>00:02.254</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>00:01.066</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>00:00.211</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>00:34.533</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>00:02.233</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>00:01.042</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>00:00.189</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 f6eedd0c3..b04401434 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: 5951us [5951us] (45.17%; 45.17%)
-FoldScaleAxis: 7223us [2us] (54.83%; 54.83%)
- FoldConstant: 7221us [1478us] (54.81%; 99.97%)
- InferType: 5742us [5742us] (43.59%; 79.53%)
+InferType: 5904us [5904us] (45.07%; 45.07%)
+FoldScaleAxis: 7195us [3us] (54.93%; 54.93%)
+ FoldConstant: 7193us [1488us] (54.91%; 99.96%)
+ InferType: 5705us [5705us] (43.55%; 79.32%)
</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: 5775us [5775us] (44.69%; 44.69%)
-FoldScaleAxis: 7148us [2us] (55.31%; 55.31%)
- FoldConstant: 7146us [1494us] (55.30%; 99.97%)
- InferType: 5652us [5652us] (43.73%; 79.09%)
+InferType: 5779us [5779us] (44.90%; 44.90%)
+FoldScaleAxis: 7092us [2us] (55.10%; 55.10%)
+ FoldConstant: 7090us [1477us] (55.09%; 99.97%)
+ InferType: 5613us [5613us] (43.61%; 79.16%)
</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 7bd0784f7..1acdc43a8 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</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>Convolution: 54.112776 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.266199 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 99042f023..cede0d7e8 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</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>conv2d with tensor core: 6.620475 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.060039 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 c0652789c..672a657e40 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ 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: 0.018746
-Baseline: 3.440995
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.017987
+Baseline: 3.197950
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ 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: 0.295498
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.296741
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ 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: 0.333418
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332394
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ 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: 0.116125
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115559
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ 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: 0.110524
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110634
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</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: 0.110295
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.110050
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ 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: 0.144898
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.142357
</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 8fce2683b..c39a0d8a6 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>00:35.062</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.007</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.392</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>00:01.422</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>00:01.248</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>00:31.396</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>00:01.379</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>00:01.232</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 49bc8197e..9b8c77e2f 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>05:01.430</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:01.238</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:24.580</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>01:20.324</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>00:40.309</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>00:18.986</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>00:08.829</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>00:08.403</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>02:16.925</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>01:20.526</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>00:40.173</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>00:26.196</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>00:09.060</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>00:08.357</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 8d1021758..b9d2f6dbd 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
@@ -470,12 +470,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1008]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [384]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -489,802 +489,465 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1008], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= threadIdx.x_1) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((cse_var_2 + threadIdx.x_1) + rx.outer.outer) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 28)] = @tir.if_then_else(((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, 7) + 4)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @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) + 8), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(thre [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 84)] = @tir.if_then_else(((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) + 12), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @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) + 16), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 140)] = @tir.if_then_else(((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) + 20), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @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) + 24), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((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) + 28), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else((((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) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 252)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 188)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((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) + 40), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 308)] = @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) + 44), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((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) + 48), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 364)] = @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) + 52), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((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, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 420)] = @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) + 60), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((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) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 476)] = @tir.if_then_else((((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) + 68), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 384)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 532)] = @tir.if_then_else(((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) + 76), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @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) + 80), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((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) + 84), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @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) + 88), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 644)] = @tir.if_then_else(((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) + 92), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 672)] = @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) + 96), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 700)] = @tir.if_then_else(((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) + 100), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 728)] = @tir.if_then_else((((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) + 104), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 756)] = @tir.if_then_else((((7 <= threadIdx.x_1) && (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, 7)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) + 580)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((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, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 812)] = @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) + 116), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + rx.outer.outer) + floormod(t [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 840)] = @tir.if_then_else(((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) + 120), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 868)] = @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) + 124), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(t [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 896)] = @tir.if_then_else(((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) + 128), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 924)] = @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) + 132), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 6), 9)*7)) + rx.outer.outer) + floormod(t [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 952)] = @tir.if_then_else(((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) + 136), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else((((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) + 140), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [384], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 7), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 56)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 84)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 21), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 36), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 140)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 35), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 44), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 168)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 42), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 24), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 4), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 252)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 63), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 12), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 280)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 70), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 40), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 308)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 77), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 20), 48)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2*3)) + rx.outer.outer) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 20), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[(((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 91), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 28), 48)*3)) + rx.outer.outer)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7)*7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 3)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 4)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 5)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 6)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 192)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 66)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 67)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 68)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 69)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 195)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 129)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 130)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 131)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 132)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 192)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 193)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 194)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 195)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 201)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 255)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 256)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 257)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 258)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 204)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 318)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 319)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 320)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 321)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 381)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 382)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 383)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 384)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 210)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 444)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 445)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 446)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 447)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 213)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 507)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 508)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 509)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 510)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 570)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 571)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 572)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 573)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 219)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 633)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 634)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 635)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 636)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 222)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 694)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 695)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 696)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 697)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 698)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 699)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 757)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 758)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 759)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 760)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 761)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 762)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 228)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 822)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 823)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 824)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 825)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 231)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 883)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 884)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 885)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 886)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 887)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 888)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 946)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 947)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 948)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 949)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 950)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 951)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 237)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 8)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 12)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 13)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 193)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 71)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 75)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 76)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 196)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 134)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 138)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 139)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 197)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 201)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 202)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 260)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 264)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 265)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 323)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 327)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 328)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 386)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 390)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 391)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 211)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 449)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 453)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 454)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 214)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 512)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 516)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 517)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 575)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 579)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 580)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 220)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 638)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 642)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 643)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 223)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 701)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 702)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 703)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 704)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 705)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 706)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 764)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 765)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 766)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 767)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 768)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 769)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 229)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 827)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 831)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 832)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 232)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 890)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 894)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 895)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 953)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 954)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 955)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 956)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 957)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 958)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 238)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 15)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 16)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 17)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 194)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 78)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 79)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 80)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 197)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 141)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 142)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 143)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 204)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 205)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 206)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 203)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 267)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 268)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 269)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 206)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 330)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 331)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 332)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 393)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 394)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 395)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 212)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 456)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 457)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 458)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 215)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 519)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 520)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 521)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 582)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 583)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 584)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 221)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 645)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 646)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 647)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 224)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 708)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 709)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 710)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 711)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 712)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 713)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 771)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 772)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 773)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 774)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 775)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 776)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 230)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 834)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 835)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 836)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 837)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 838)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 839)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 233)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 897)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 898)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 899)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 960)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 961)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 962)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 963)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 964)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((floormod(threadIdx.x, 7)*7) + 965)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*48) + 239)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 832), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1024), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1088), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1216), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1280), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1408), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1472), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1600), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1664), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1792), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1856), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1984), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2048), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2176), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2240), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2368), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2432), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2560), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2624), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2752), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2816), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2944), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 3008), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- compute[((blockIdx.x*392) + (threadIdx.x*7))] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 1)] = max((conv2d_nchw_1[1] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 2)] = max((conv2d_nchw_1[2] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 3)] = max((conv2d_nchw_1[3] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 4)] = max((conv2d_nchw_1[4] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 5)] = max((conv2d_nchw_1[5] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 6)] = max((conv2d_nchw_1[6] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 196)] = max((conv2d_nchw_1[7] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 197)] = max((conv2d_nchw_1[8] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 198)] = max((conv2d_nchw_1[9] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 199)] = max((conv2d_nchw_1[10] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 200)] = max((conv2d_nchw_1[11] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 201)] = max((conv2d_nchw_1[12] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- compute[(((blockIdx.x*392) + (threadIdx.x*7)) + 202)] = max((conv2d_nchw_1[13] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
+ }
}
}
</pre></div>
@@ -1321,7 +984,7 @@ cooperative fetching, unrolling and operator fusion.</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>Execution time of this operator: 0.426 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.361 ms
</pre></div>
</div>
</div>
@@ -1352,36 +1015,36 @@ conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=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_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -1400,14 +1063,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=28)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1425,10 +1088,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(28) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[1008];
- __shared__ float kernel_shared[384];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1443,750 +1106,413 @@ extern "C" __global__ void __launch_bounds__(28) default_function_kern
conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 28)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 20)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((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 * 784) + (((((int)threadIdx.x) + 56) / 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) + 84)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 84) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((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 * 784) + (((((int)threadIdx.x) + 112) / 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) + 140)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 140) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = (((((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 * 784) + (((((int)threadIdx.x) + 168) / 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) + 196)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 224) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 252)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 188)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 280) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 308)] = (((((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 * 784) + (((((int)threadIdx.x) + 308) / 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) + 336)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 336) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 364)] = (((((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 * 784) + (((((int)threadIdx.x) + 364) / 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) + 392)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 420)] = (((((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 * 784) + (((((int)threadIdx.x) + 420) / 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) + 448)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 448) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 476)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 476) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 384)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 532)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 532) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((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 * 784) + (((((int)threadIdx.x) + 560) / 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) + 588)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 616)] = (((((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 * 784) + (((((int)threadIdx.x) + 616) / 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) + 644)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 644) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 672)] = (((((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 * 784) + (((((int)threadIdx.x) + 672) / 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) + 700)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 700) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 728)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 728) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 756)] = ((((7 <= ((int)threadIdx.x)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((rc_outer_outer * 784) + ((int)threadIdx.x)) + rx_outer_outer) + 580)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 4) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 812)] = (((((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 * 784) + (((((int)threadIdx.x) + 812) / 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) + 840)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 840) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 3) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 868)] = (((((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 * 784) + (((((int)threadIdx.x) + 868) / 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) + 896)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 896) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 2) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 924)] = (((((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 * 784) + (((((int)threadIdx.x) + 924) / 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) + 952)] = (((1 <= (rx_outer_outer + (((int)threadIdx.x) % 7))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 952) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = ((((((int)threadIdx.x) < 21) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 5) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 28) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 28) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 8) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 84) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 36) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 16) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 140) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 44) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 24) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 4) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 32) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 12) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 48) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) + 40) % 48) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 308)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 20) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 3)) + rx_outer_outer) + 32256)];
- if (((int)threadIdx.x) < 20) {
- kernel_shared[(((int)threadIdx.x) + 364)] = kernel[(((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 48) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 28) * 3)) + rx_outer_outer)];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
}
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[((((int)threadIdx.x) / 7) * 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) * 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 3)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 4)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 5)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 6)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 192)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 66)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 67)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 68)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 69)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 195)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 129)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 130)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 131)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 132)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 192)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 193)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 194)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 195)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 201)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 255)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 256)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 257)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 258)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 318)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 319)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 320)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 321)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 381)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 382)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 383)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 384)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 444)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 445)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 446)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 447)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 213)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 507)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 508)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 509)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 510)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 570)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 571)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 572)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 573)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 219)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 633)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 634)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 635)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 636)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 222)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 693)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 694)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 695)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 696)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 697)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 698)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 699)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 756)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 757)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 758)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 759)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 760)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 761)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 762)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 228)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 819)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 820)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 821)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 822)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 823)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 824)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 825)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 231)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 882)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 883)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 884)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 885)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 886)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 887)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 888)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 945)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 946)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 947)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 948)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 949)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 950)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 951)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 237)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 8)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 12)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 13)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 193)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 70)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 71)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 75)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 76)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 196)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 133)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 134)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 138)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 139)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 196)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 197)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 201)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 202)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 259)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 260)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 264)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 265)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 322)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 323)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 327)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 328)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 385)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 386)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 390)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 391)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 211)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 448)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 449)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 453)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 454)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 214)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 511)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 512)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 516)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 517)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 574)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 575)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 579)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 580)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 220)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 637)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 638)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 642)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 643)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 223)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 700)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 701)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 702)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 703)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 704)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 705)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 706)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 763)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 764)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 765)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 766)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 767)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 768)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 769)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 229)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 826)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 827)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 828)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 829)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 830)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 831)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 832)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 232)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 889)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 890)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 891)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 892)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 893)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 894)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 895)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 952)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 953)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 954)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 955)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 956)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 957)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 958)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 238)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 14)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 15)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 16)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 17)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 194)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 77)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 78)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 79)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 80)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 197)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 140)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 141)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 142)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 143)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 203)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 204)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 205)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 206)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 203)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 266)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 267)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 268)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 269)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 206)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 329)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 330)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 331)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 332)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 392)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 393)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 394)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 395)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 212)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 455)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 456)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 457)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 458)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 215)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 518)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 519)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 520)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 521)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 581)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 582)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 583)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 584)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 221)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 644)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 645)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 646)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 647)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 648)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 649)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 650)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 224)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 707)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 708)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 709)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 710)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 711)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 712)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 713)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 770)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 771)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 772)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 773)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 774)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 775)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 776)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 230)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 833)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 834)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 835)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 836)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 837)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 838)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 839)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 233)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 896)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 897)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 898)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 899)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 900)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 901)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 902)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 959)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 960)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 961)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 962)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 963)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 964)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((((int)threadIdx.x) % 7) * 7) + 965)] * kernel_shared[(((((int)threadIdx.x) / 7) * 48) + 239)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ }
+ }
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
- compute[((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 1)] = max((conv2d_nchw[1] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 2)] = max((conv2d_nchw[2] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 3)] = max((conv2d_nchw[3] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 4)] = max((conv2d_nchw[4] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 5)] = max((conv2d_nchw[5] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 6)] = max((conv2d_nchw[6] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 196)] = max((conv2d_nchw[7] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 197)] = max((conv2d_nchw[8] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 198)] = max((conv2d_nchw[9] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 199)] = max((conv2d_nchw[10] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 200)] = max((conv2d_nchw[11] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 201)] = max((conv2d_nchw[12] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
- compute[(((((int)blockIdx.x) * 392) + (((int)threadIdx.x) * 7)) + 202)] = max((conv2d_nchw[13] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -2223,7 +1549,7 @@ 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 24.580 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 16.925 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 e52ef446c..bdda6121e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ 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)
- 9.8081 9.8166 9.8597 9.7480 0.0460
+ 9.9311 9.9254 9.9468 9.9212 0.0112
</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 b008826d4..aabc0f85d 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ 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)
- 756.7165 755.7170 761.7452 752.6874 3.7648
+ 763.0553 762.3600 769.1978 757.6080 4.7570
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ 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 20.324 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.526 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 879c62058..88e9332b7 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,78 +600,121 @@ 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_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = (((i.outer.inner*1024) + (i.inner.init*32)) + (nb_j.inner*16))
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 1024) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ let cse_var_2: int32 = (nb_j.inner*16)
+ let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ {
+ compute_5: Buffer(compute_4, float32, [64], [])[cse_var_2] = 0f32
+ compute_5[(cse_var_2 + 1)] = 0f32
+ compute_5[(cse_var_2 + 2)] = 0f32
+ compute_5[(cse_var_2 + 3)] = 0f32
+ compute_5[(cse_var_2 + 4)] = 0f32
+ compute_5[(cse_var_2 + 5)] = 0f32
+ compute_5[(cse_var_2 + 6)] = 0f32
+ compute_5[(cse_var_2 + 7)] = 0f32
+ compute_5[(cse_var_2 + 8)] = 0f32
+ compute_5[(cse_var_2 + 9)] = 0f32
+ compute_5[(cse_var_2 + 10)] = 0f32
+ compute_5[(cse_var_2 + 11)] = 0f32
+ compute_5[(cse_var_2 + 12)] = 0f32
+ compute_5[(cse_var_2 + 13)] = 0f32
+ compute_5[(cse_var_2 + 14)] = 0f32
+ compute_5[(cse_var_2 + 15)] = 0f32
+ compute_5[(cse_var_2 + 32)] = 0f32
+ compute_5[(cse_var_2 + 33)] = 0f32
+ compute_5[(cse_var_2 + 34)] = 0f32
+ compute_5[(cse_var_2 + 35)] = 0f32
+ compute_5[(cse_var_2 + 36)] = 0f32
+ compute_5[(cse_var_2 + 37)] = 0f32
+ compute_5[(cse_var_2 + 38)] = 0f32
+ compute_5[(cse_var_2 + 39)] = 0f32
+ compute_5[(cse_var_2 + 40)] = 0f32
+ compute_5[(cse_var_2 + 41)] = 0f32
+ compute_5[(cse_var_2 + 42)] = 0f32
+ compute_5[(cse_var_2 + 43)] = 0f32
+ compute_5[(cse_var_2 + 44)] = 0f32
+ compute_5[(cse_var_2 + 45)] = 0f32
+ compute_5[(cse_var_2 + 46)] = 0f32
+ compute_5[(cse_var_2 + 47)] = 0f32
+ for (elem_idx: int32, 0, (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ let cse_var_35: int32 = (cse_var_2 + 10)
+ let cse_var_34: int32 = (cse_var_2 + 11)
+ let cse_var_33: int32 = (cse_var_2 + 12)
+ let cse_var_32: int32 = (cse_var_2 + 13)
+ let cse_var_31: int32 = (cse_var_2 + 14)
+ let cse_var_30: int32 = (cse_var_2 + 15)
+ let cse_var_29: int32 = (cse_var_2 + 2)
+ let cse_var_28: int32 = (cse_var_2 + 3)
+ let cse_var_27: int32 = (cse_var_2 + 32)
+ let cse_var_26: int32 = (cse_var_2 + 33)
+ let cse_var_25: int32 = (cse_var_2 + 34)
+ let cse_var_24: int32 = (cse_var_2 + 35)
+ let cse_var_23: int32 = (cse_var_2 + 36)
+ let cse_var_22: int32 = (cse_var_2 + 37)
+ let cse_var_21: int32 = (cse_var_2 + 38)
+ let cse_var_20: int32 = (cse_var_2 + 1)
+ let cse_var_19: int32 = (elem_idx*16)
+ let cse_var_18: int32 = (cse_var_2 + 9)
+ let cse_var_17: int32 = (cse_var_2 + 8)
+ let cse_var_16: int32 = (cse_var_2 + 7)
+ let cse_var_15: int32 = (cse_var_2 + 6)
+ let cse_var_14: int32 = (cse_var_2 + 5)
+ let cse_var_13: int32 = (cse_var_2 + 47)
+ let cse_var_12: int32 = (cse_var_2 + 46)
+ let cse_var_11: int32 = (cse_var_2 + 45)
+ let cse_var_10: int32 = (cse_var_2 + 44)
+ let cse_var_9: int32 = (cse_var_2 + 43)
+ let cse_var_8: int32 = (cse_var_2 + 42)
+ let cse_var_7: int32 = (cse_var_2 + 41)
+ let cse_var_6: int32 = (cse_var_2 + 40)
+ let cse_var_5: int32 = (cse_var_2 + 39)
+ let cse_var_4: int32 = (cse_var_2 + 4)
+ let cse_var_3: int32 = (floordiv(i0.outer.i1.outer.fused, 16)*512)
{
- compute_5: Buffer(compute_4, float32, [4096], [])[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 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*1024) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 1)
- let cse_var_16: int32 = (cse_var_18 + 11)
- let cse_var_15: int32 = (cse_var_18 + 12)
- let cse_var_14: int32 = (cse_var_18 + 13)
- let cse_var_13: int32 = (cse_var_18 + 14)
- let cse_var_12: int32 = (cse_var_18 + 15)
- let cse_var_11: int32 = (cse_var_18 + 2)
- let cse_var_10: int32 = (cse_var_18 + 3)
- let cse_var_9: int32 = (cse_var_18 + 4)
- let cse_var_8: int32 = (cse_var_18 + 5)
- let cse_var_7: int32 = (cse_var_18 + 6)
- let cse_var_6: int32 = (cse_var_18 + 7)
- let cse_var_5: int32 = (cse_var_18 + 8)
- let cse_var_4: int32 = (cse_var_18 + 9)
- let cse_var_3: int32 = (cse_var_18 + 10)
- {
- compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_19)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_29] = (compute_5[cse_var_29] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_28] = (compute_5[cse_var_28] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_35] = (compute_5[cse_var_35] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_34] = (compute_5[cse_var_34] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_33] = (compute_5[cse_var_33] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_32] = (compute_5[cse_var_32] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_31] = (compute_5[cse_var_31] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_30] = (compute_5[cse_var_30] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)])], 0f32)))
+ compute_5[cse_var_27] = (compute_5[cse_var_27] + (placeholder_1[((placeholder_3[cse_var_1]*16) + cse_var_19)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_26] = (compute_5[cse_var_26] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 1)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_25] = (compute_5[cse_var_25] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 2)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_24] = (compute_5[cse_var_24] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 3)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_23] = (compute_5[cse_var_23] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 4)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_22] = (compute_5[cse_var_22] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 5)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_21] = (compute_5[cse_var_21] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 6)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 7)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 8)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 9)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 10)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 11)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 12)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 13)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 14)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_1]*16) + cse_var_19) + 15)]*max(placeholder[((cse_var_3 + placeholder_2[(placeholder_3[cse_var_1] + elem_idx)]) + 256)], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*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))
+ for (i0.inner: int32, 0, 2) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_36: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*1024) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_36] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_36]), 0f32)
+ }
}
}
}
@@ -710,7 +753,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</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>Execution time of this operator: 1.760 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.021 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 7c35500ed..d075f640b 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>00:44.393</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.424</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.515</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>00:00.229</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>00:00.221</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>00:00.219</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>00:00.209</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>00:43.539</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>00:00.231</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>00:00.220</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>00:00.218</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_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 f11c02fd1..e700fd4bb 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: 65.32/65.32 result: MeasureResult(costs=(0.003544183166666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5835719108581543, timestamp=1651513383.1706367) [('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: 0.00/65.32 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.21/110.21 result: MeasureResult(costs=(0.0021005143958333335,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.7704191207885742, timestamp=1651514766.3382714) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.21 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: 0.00/65.32 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.21 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: 0.00/65.32 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.21 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: 0x00007f01a8762fa2
+ 12: 0x00007f4d48ccffa2
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: 144.87/144.87 result: MeasureResult(costs=(0.00159799916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4261679649353027, timestamp=1651513409.5856156) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 144.30/144.30 result: MeasureResult(costs=(0.00160430183,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.435715913772583, timestamp=1651514792.7239048) [('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,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.001950
+Time cost of this operator: 0.002049
</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 2cc6e97b6..4d2685432 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.6 98.712 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.156 0.997 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 0.291 (1, 1, 10, 10, 3) 1 1
-Total_time - 316.677 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.7 98.753 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.951 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.954 0.296 (1, 1, 10, 10, 3) 1 1
+Total_time - 322.724 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ 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 136.3 98.072 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 1.25 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.941 0.677 (1, 1, 10, 10, 3) 1 1
-Total_time - 138.979 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 82.65 96.906 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 2.038 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 1.056 (1, 1, 10, 10, 3) 1 1
+Total_time - 85.289 - - - -
</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 e4f5fcd4f..8505460e4 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>00:44.155</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:43.649</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.084</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>00:03.474</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>00:00.203</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>00:00.198</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>00:00.195</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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:39.588</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>00:03.453</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>00:00.223</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</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>00:00.192</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 9d0257941..45839da31 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>00:09.381</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.339</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:06.875</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>00:02.292</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>00:00.214</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>00:07.509</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>00:01.610</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>00:00.220</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 c5f48b4b4..6dca2a724 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>00:05.646</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.580</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.073</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>00:01.104</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>00:00.723</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>00:00.722</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>00:00.317</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>00:00.249</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>00:00.231</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>00:00.227</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>00:02.046</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>00:01.146</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>00:00.712</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>00:00.693</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>00:00.305</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>00:00.230</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>00:00.227</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>00:00.222</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>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 6fb7cee3c..d6ebbcc3a 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/tmppjo2db3s/input0.cc'\nsource_filename = \"/tmp/tmppjo2db3s/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/tmpu39gg2mj/input0.cc'\nsource_filename = \"/tmp/tmpu39gg2mj/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 5e0618de0..db0c99abd 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ 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">
@@ -1750,7 +1750,7 @@ 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 dd36adcd3..0f362c26e 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/be90c656e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 b998ec106..fe532031e 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/be90c656e/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 4aa1f029b..5b53a9b5e 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/be90c656e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 3886b5f50..d32dd2dc9 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/be90c656e/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 a2bc3ffc5..46efaba56 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/be90c656e/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 103029c4d..8cb921f74 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/be90c656e/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 576f48061..39c8f8f69 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/be90c656e/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 b92c0ecaa..98d536054 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/be90c656e/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 0a996d6a6..846e16e74 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/be90c656e/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 ad58cf66e..644321655 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/be90c656e/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 0e262ac08..673e72419 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/be90c656e/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 d9785ddc1..95ba80b36 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/be90c656e/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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 a4f190cfb..0cfe7e2df 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/be90c656e/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/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/be90c656e/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 3bda87906..c030a29fe 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 519d5894a..3e9e534c2 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 9ef2cc2c8..8e2c20fa9 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 0a716eec1..d52611170 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 3e2c9f55a..431f66d9a 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 2548fe944..81943fcd1 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index e4e84b212..f2997af63 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index b14c37845..67e2d69a8 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/be90c656e/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9284d32e3/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
... 987 lines suppressed ...