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 2022/04/05 05:35:19 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4b3b86c2c33c3c56c49afec4452a05ffbbfdc9da)
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 76e200bc2 deploying docs (apache/tvm@4b3b86c2c33c3c56c49afec4452a05ffbbfdc9da)
76e200bc2 is described below
commit 76e200bc2674f07337c24822e501908e866364b7
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Apr 5 05:35:15 2022 +0000
deploying docs (apache/tvm@4b3b86c2c33c3c56c49afec4452a05ffbbfdc9da)
---
.../how_to/compile_models/from_mxnet.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 | 20 +-
.../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 | 3531 +++++++-------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 82 +-
.../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 | 4 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 22 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 20 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 75 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 47 +-
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 | 3531 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 82 +-
.../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 | 4 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_relay_x86.html | 168 +-
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 +-
113 files changed, 3380 insertions(+), 5378 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 65b25e7c7..3b5988d5a 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.zipb439d238-b07d-4023-a0be-b6a7a7540d22 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip277f5cb8-022f-41ac-b5d1-9b53b8480533 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_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 5977683b1..0bf695290 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 7.176 seconds)
+ **Total running time of the script:** ( 1 minutes 3.781 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 653841dd3..4a0e299a7 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]
6%|5 | 2.50M/44.7M [00:00<00:01, 24.9MB/s]
11%|#1 | 5.01M/44.7M [00:00<00:01, 25.7MB/s]
17%|#6 | 7.46M/44.7M [00:00<00:01, 25.3MB/s]
22%|##2 | 9.88M/44.7M [00:00<00:01, 25.0MB/s]
27%|##7 | 12.3M/44.7M [00:00<00:01, 23.3MB/s]
32%|###2 | 14.5M/44.7M [00:00<00:01, 22.3MB/s]
38%|###7 | 16.9M/44.7M [00:00<00:01, 22.9MB/s]
43%|####2 | 19.1M/44.7M [00:00<00:01, 23.1MB/s]
48%|####7 | 21.3M/44.7M [00:00<00:01, 22.2MB/s]
53%|#####3 | 23.8M/44.7M [00:01<00:00, 23.0MB/s]
58%|#####8 | 26.1M/44.7M [00:01<00:00, 23.4MB/s]
64%|######3 | 28.4M/44.7M [00:01<00:00, 22.6MB/s]
69%|######8 | 30.7M/44.7M [00:01<00:00, 23.1MB/s]
74%|#######4 | 33.1M/44.7M [00:01<00:00, 23.5MB/s]
79%|#######9 | 35.5M/44.7M [00:01<00:00, 23.9MB/s]
85%|########4 | 37.8M/44.7M [00:01<00:00, 23.9MB/s]
90%|########9 | 40.1M/44.7M [00
:01<00:00, 24.0MB/s]
95%|#########5| 42.4M/44.7M [00:01<00:00, 24.1MB/s]
100%|##########| 44.7M/44.7M [00:01<00:00, 23.6MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
87%|########7 | 39.0M/44.7M [00:00<00:00, 210MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 210MB/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 dc27d67bb..f4d7b596e 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 4.684 seconds)
+ **Total running time of the script:** ( 1 minutes 2.125 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 b5ee68741..12c880d28 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
@@ -5,14 +5,14 @@
Computation times
=================
-**04:57.161** total execution time for **how_to_compile_models** files:
+**04:44.749** total execution time for **how_to_compile_models** files:
-- **01:07.176**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:04.684**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.006**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:25.525**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.635**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.642**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:20.808**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.098**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.586**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:03.781**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:02.125**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:56.184**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:25.422**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.198**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.988**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:18.599**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.659**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.794**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index ee9f4c4ec..63b8e0f70 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)
- 16.3039 16.3235 16.4023 16.2080 0.0673
+ 16.2752 16.2673 16.5289 16.0850 0.1057
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 03825e591..5615b3a4b 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]
3%|3 | 5.69M/170M [00:00<00:02, 59.3MB/s]
7%|6 | 11.3M/170M [00:00<00:03, 54.1MB/s]
10%|9 | 16.5M/170M [00:00<00:03, 45.3MB/s]
13%|#3 | 22.4M/170M [00:00<00:03, 50.8MB/s]
16%|#6 | 27.4M/170M [00:00<00:03, 46.4MB/s]
20%|#9 | 33.2M/170M [00:00<00:02, 50.4MB/s]
23%|##2 | 39.1M/170M [00:00<00:02, 53.8MB/s]
26%|##6 | 44.7M/170M [00:00<00:02, 55.3MB/s]
29%|##9 | 50.1M/170M [00:01<00:02, 52.5MB/s]
33%|###3 | 56.2M/170M [00:01<00:02, 55.9MB/s]
37%|###6 | 62.0M/170M [00:01<00:01, 57.4MB/s]
40%|###9 | 67.6M/170M [00:01<00:01, 56.9MB/s]
43%|####3 | 73.1M/170M [00:01<00:01, 56.1MB/s]
46%|####6 | 78.4M/170M [00:01<00:01, 49.3MB/s]
49%|####9 | 84.1M/170M [00:01<00:01, 51.8MB/s]
53%|#####3 | 90.6M/170M [00:01<00:01, 56.5MB/s]
57%|#####6 | 96.2M/170M [00:01<00:01, 56.4MB/
s]
60%|#####9 | 102M/170M [00:02<00:01, 53.1MB/s]
63%|######3 | 108M/170M [00:02<00:01, 55.4MB/s]
66%|######6 | 113M/170M [00:02<00:01, 55.5MB/s]
70%|######9 | 118M/170M [00:02<00:00, 55.5MB/s]
73%|#######2 | 124M/170M [00:02<00:00, 55.6MB/s]
76%|#######5 | 129M/170M [00:02<00:00, 55.2MB/s]
79%|#######9 | 134M/170M [00:02<00:00, 48.2MB/s]
82%|########1 | 139M/170M [00:02<00:00, 45.2MB/s]
85%|########4 | 144M/170M [00:02<00:00, 48.2MB/s]
88%|########7 | 149M/170M [00:02<00:00, 49.5MB/s]
91%|#########1| 155M/170M [00:03<00:00, 52.7MB/s]
94%|#########4| 160M/170M [00:03<00:00, 52.3MB/s]
97%|#########7| 165M/170M [00:03<00:00, 51.5MB/s]
100%|##########| 170M/170M [00:03<00:00, 51.7MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 2.25M/170M [00:00<00:07, 22.5MB/s]
3%|3 | 5.12M/170M [00:00<00:06, 26.4MB/s]
6%|5 | 9.80M/170M [00:00<00:04, 36.5MB/s]
8%|7 | 13.4M/170M [00:00<00:04, 36.7MB/s]
10%|# | 17.5M/170M [00:00<00:04, 39.1MB/s]
13%|#2 | 21.6M/170M [00:00<00:03, 40.3MB/s]
15%|#5 | 25.7M/170M [00:00<00:03, 41.0MB/s]
17%|#7 | 29.7M/170M [00:00<00:04, 34.6MB/s]
20%|#9 | 33.4M/170M [00:00<00:04, 35.6MB/s]
22%|##1 | 36.9M/170M [00:01<00:04, 30.2MB/s]
24%|##3 | 40.4M/170M [00:01<00:04, 31.7MB/s]
26%|##5 | 43.5M/170M [00:01<00:04, 29.5MB/s]
28%|##8 | 47.6M/170M [00:01<00:03, 32.8MB/s]
30%|### | 51.7M/170M [00:01<00:03, 35.5MB/s]
33%|###2 | 55.2M/170M [00:01<00:03, 34.7MB/s]
35%|###4 | 59.4M/170M [00:01<00:03, 35.6MB/s]
37%|###7 | 62.8M/170M [00:01<00:03, 35.2MB/
s]
39%|###9 | 67.0M/170M [00:02<00:02, 37.5MB/s]
42%|####1 | 70.6M/170M [00:02<00:02, 37.4MB/s]
44%|####3 | 74.2M/170M [00:02<00:02, 35.0MB/s]
46%|####5 | 77.6M/170M [00:02<00:03, 31.4MB/s]
49%|####8 | 82.6M/170M [00:02<00:02, 35.2MB/s]
51%|##### | 86.0M/170M [00:02<00:02, 34.1MB/s]
53%|#####2 | 89.3M/170M [00:02<00:02, 32.3MB/s]
55%|#####4 | 93.0M/170M [00:02<00:02, 33.9MB/s]
57%|#####7 | 97.2M/170M [00:02<00:02, 36.8MB/s]
60%|#####9 | 101M/170M [00:03<00:01, 37.8MB/s]
62%|######2 | 106M/170M [00:03<00:01, 41.4MB/s]
65%|######5 | 111M/170M [00:03<00:01, 44.7MB/s]
68%|######7 | 115M/170M [00:03<00:01, 42.6MB/s]
70%|####### | 120M/170M [00:03<00:01, 37.6MB/s]
73%|#######2 | 123M/170M [00:03<00:01, 36.6MB/s]
76%|#######5 | 129M/170M [00:03<00:01, 42.3MB/s]
78%|#######8 | 133M/170M [00:03<00:00, 41.5MB/s]
81%|########1 | 138M/170M [00:03<00:00, 43.5
MB/s]
84%|########3 | 143M/170M [00:04<00:00, 44.9MB/s]
87%|########6 | 147M/170M [00:04<00:00, 45.5MB/s]
89%|########9 | 152M/170M [00:04<00:00, 44.7MB/s]
92%|#########2| 156M/170M [00:04<00:00, 45.6MB/s]
95%|#########4| 161M/170M [00:04<00:00, 41.0MB/s]
98%|#########7| 166M/170M [00:04<00:00, 44.6MB/s]
100%|##########| 170M/170M [00:04<00:00, 37.9MB/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 15.666 seconds)
+ **Total running time of the script:** ( 3 minutes 7.160 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 6a07d05cb..b66021fee 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, 205MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
36%|###5 | 4.83M/13.6M [00:00<00:00, 50.6MB/s]
74%|#######3 | 9.99M/13.6M [00:00<00:00, 52.7MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 40.5MB/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)
- 90.6596 90.4672 96.6449 90.2357 0.8152
+ 90.1404 90.0909 90.8977 89.9211 0.1899
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.434 seconds)
+ **Total running time of the script:** ( 1 minutes 4.147 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 a23c7ad88..73ca6b965 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)
- 120.0871 119.9965 128.7969 119.2630 0.9346
+ 120.8911 120.9887 127.1042 118.9195 1.0356
@@ -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 54.477 seconds)
+ **Total running time of the script:** ( 1 minutes 53.531 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 fd51dab6f..d738d9dbd 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 13.899 seconds)
+ **Total running time of the script:** ( 1 minutes 10.123 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 54228429f..375be844a 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]
0%| | 323/132723 [00:00<00:44, 2950.93KB/s]
1%|1 | 1606/132723 [00:00<00:15, 8543.58KB/s]
2%|2 | 3076/132723 [00:00<00:11, 10822.33KB/s]
5%|5 | 6859/132723 [00:00<00:05, 21074.39KB/s]
8%|7 | 10318/132723 [00:00<00:04, 25823.47KB/s]
11%|#1 | 14785/132723 [00:00<00:03, 32122.89KB/s]
14%|#3 | 18035/132723 [00:00<00:05, 22823.67KB/s]
16%|#5 | 21063/132723 [00:00<00:04, 24639.01KB/s]
18%|#7 | 23833/132723 [00:01<00:04, 23625.71KB/s]
20%|#9 | 26406/132723 [00:01<00:04, 24074.79KB/s]
22%|##1 | 29104/132723 [00:01<00:04, 24795.63KB/s]
24%|##3 | 31701/132723 [00:01<00:04, 22995.87KB/s]
26%|##5 | 34136/132723 [00:01<00:04, 23347.37KB/s]
30%|### | 40459/132723 [00:01<00:02, 34303.66KB/s]
34%|###3 | 45117/132723 [00:01<00:02, 37762.67KB/s]
39%|###9 | 52273
/132723 [00:01<00:01, 47462.17KB/s]
43%|####3 | 57162/132723 [00:01<00:01, 42813.06KB/s]
48%|####7 | 63450/132723 [00:02<00:01, 48113.90KB/s]
52%|#####1 | 68748/132723 [00:02<00:01, 49316.90KB/s]
57%|#####7 | 75823/132723 [00:02<00:01, 55401.37KB/s]
61%|######1 | 81493/132723 [00:02<00:01, 47677.35KB/s]
66%|######5 | 87110/132723 [00:02<00:00, 49574.97KB/s]
71%|#######1 | 94391/132723 [00:02<00:00, 55846.37KB/s]
76%|#######5 | 100566/132723 [00:02<00:00, 57473.23KB/s]
80%|######## | 106480/132723 [00:02<00:00, 50895.46KB/s]
86%|########6 | 114296/132723 [00:02<00:00, 58065.84KB/s]
92%|#########2| 122288/132723 [00:03<00:00, 64033.68KB/s]
98%|#########8| 130312/132723 [00:03<00:00, 68580.22KB/s]
100%|##########| 132723/132723 [00:03<00:00, 41515.10KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
6%|5 | 7302/132723 [00:00<00:01, 73010.15KB/s]
11%|#1 | 15153/132723 [00:00<00:01, 76242.22KB/s]
18%|#8 | 24070/132723 [00:00<00:01, 82140.31KB/s]
25%|##4 | 32988/132723 [00:00<00:01, 84913.76KB/s]
32%|###1 | 41907/132723 [00:00<00:01, 86452.58KB/s]
38%|###8 | 50875/132723 [00:00<00:00, 87547.79KB/s]
45%|####4 | 59630/132723 [00:00<00:00, 85505.68KB/s]
52%|#####1 | 68568/132723 [00:00<00:00, 86717.34KB/s]
58%|#####8 | 77514/132723 [00:00<00:00, 87561.81KB/s]
65%|######5 | 86495/132723 [00:01<00:00, 88248.92KB/s]
72%|#######1 | 95448/132723 [00:01<00:00, 88636.20KB/s]
79%|#######8 | 104397/132723 [00:01<00:00, 88891.45KB/s]
85%|########5 | 113289/132723 [00:01<00:00, 88700.82KB/s]
92%|#########2| 122162/132723 [00:01<00:00, 86876.44KB/s]
99%|#########8| 131146/132723 [00:01<00:00, 87752.51KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86484.10KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 30.263 seconds)
+ **Total running time of the script:** ( 2 minutes 22.164 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 17b8b4494..d0a7a83bb 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
=================
-**10:53.626** total execution time for **how_to_deploy_models** files:
+**10:26.596** total execution time for **how_to_deploy_models** files:
-- **03:15.666**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:30.263**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:54.477**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:13.899**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:07.434**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:29.638**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.040**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:07.160**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:22.164**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:53.531**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:10.123**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:04.147**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.806**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.473**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.190**: :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 8133fede2..5018db6ec 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.zip512378da-3ab2-41df-9630-50b8ac086852 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb90e6efb-e55e-4645-a72d-25f8fd8621df 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 f3f6de854..a6f5e308e 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
=================
-**00:39.696** total execution time for **how_to_extend_tvm** files:
+**00:37.934** total execution time for **how_to_extend_tvm** files:
-- **00:36.013**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.373**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.096**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.215**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.425**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.238**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.070**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.201**: :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 d08c9d5cd..6b64ed1de 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: 6200us [6200us] (45.58%; 45.58%)
- FoldScaleAxis: 7401us [3us] (54.42%; 54.42%)
- FoldConstant: 7398us [1573us] (54.40%; 99.96%)
- InferType: 5826us [5826us] (42.83%; 78.74%)
+ InferType: 6232us [6232us] (45.04%; 45.04%)
+ FoldScaleAxis: 7605us [2us] (54.96%; 54.96%)
+ FoldConstant: 7603us [1520us] (54.95%; 99.97%)
+ InferType: 6083us [6083us] (43.96%; 80.01%)
@@ -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: 5979us [5979us] (45.02%; 45.02%)
- FoldScaleAxis: 7302us [3us] (54.98%; 54.98%)
- FoldConstant: 7300us [1515us] (54.96%; 99.96%)
- InferType: 5785us [5785us] (43.56%; 79.25%)
+ InferType: 6067us [6067us] (45.38%; 45.38%)
+ FoldScaleAxis: 7304us [2us] (54.62%; 54.62%)
+ FoldConstant: 7302us [1515us] (54.61%; 99.97%)
+ InferType: 5787us [5787us] (43.28%; 79.25%)
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 9384d3701..3f0c1e6b5 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: 54.140382 ms
+ Convolution: 47.607634 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 4bb1e1398..443f9ac99 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
@@ -626,7 +626,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 8.963553 ms
+ conv2d with tensor core: 6.836040 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 ab667ddac..8e0bcf505 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: 0.019616
- Baseline: 3.454113
+ Numpy running time: 0.019144
+ Baseline: 3.251305
@@ -209,7 +209,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.325970
+ Opt1: 0.300639
@@ -307,7 +307,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.344127
+ Opt2: 0.334595
@@ -398,7 +398,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.122029
+ Opt3: 0.117366
@@ -516,7 +516,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111398
+ Opt4: 0.111272
@@ -633,7 +633,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111851
+ Opt5: 0.111764
@@ -753,7 +753,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.146843
+ Opt6: 0.144907
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 ac690fd7a..640b31d87 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
=================
-**00:35.940** total execution time for **how_to_optimize_operators** files:
+**00:34.601** total execution time for **how_to_optimize_operators** files:
-- **00:33.232**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.448**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.260**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:31.963**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.407**: :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 76f5108e0..47e595aec 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
=================
-**05:11.520** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:22.939**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.478**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.566**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:27.796**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:09.017**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.724**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:01.031** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:28.365**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.575**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.499**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:15.752**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.590**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.249**: :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 bda96696c..9bbfbb773 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
@@ -221,1139 +221,667 @@ cooperative fetching, unrolling and operator fusion.
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 784 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.outer*3136)
+ let cse_var_1: int32 = (rc.outer.outer*576)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod((threadIdx.x_1*12), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod((threadIdx.x_1*12), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod(((threadIdx.x_1*12) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod(((threadIdx.x_1*12) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 6), 9))) && (floormod(((threadIdx.x_1*12) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 7), 9))) && (floormod(((threadIdx.x_1*12) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 8), 9))) && (floormod(((threadIdx.x_1*12) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*12), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 336)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 337)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 338)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 339)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 6), 9))) && (floormod(((threadIdx.x_1*12) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 340)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 7), 9))) && (floormod(((threadIdx.x_1*12) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 341)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 8), 9))) && (floormod(((threadIdx.x_1*12) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 342)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*12), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 344)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 345)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 346)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 347)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3))]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2 + 28))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 68), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 52), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 36), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 91), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 420)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 105), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 60), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 476)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 119), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 44), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 532)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 133), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + 1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 196)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- }
+ compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
}
}
@@ -1405,7 +933,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.213 ms
+ Execution time of this operator: 0.389 ms
@@ -1451,31 +979,31 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ 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=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -1498,12 +1026,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=784)
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=12)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=784)
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, "unroll_explicit", True)
@@ -1523,1111 +1051,638 @@ 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) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[576];
+ extern "C" __global__ void __launch_bounds__(784) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[1];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && (((((int)threadIdx.x) * 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && ((((((int)threadIdx.x) * 12) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && ((((((int)threadIdx.x) * 12) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 6) % 9))) && ((((((int)threadIdx.x) * 12) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 7) % 9))) && ((((((int)threadIdx.x) * 12) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 8) % 9))) && ((((((int)threadIdx.x) * 12) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 336)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 337)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 338)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 339)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 6) % 9))) && ((((((int)threadIdx.x) * 12) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 340)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 7) % 9))) && ((((((int)threadIdx.x) * 12) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = ((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 341)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 8) % 9))) && ((((((int)threadIdx.x) * 12) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 8) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3))];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3))];
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 342)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 343)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 344)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 345)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 346)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + 1)];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + 1)];
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 347)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - 8)] : 0.000000e+00f);
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = ((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 28)];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 84) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 12))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 140) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 68) % 72))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 52) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 36))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 308)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 20))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 364)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 4))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 420)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 420) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 60) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 476)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 476) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 44))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 532)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 532) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 28))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + 2)];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + 2)];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- }
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 196)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
}
+ compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
}
@@ -2685,7 +1740,7 @@ 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 22.939 seconds)
+ **Total running time of the script:** ( 2 minutes 28.365 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 3df2fe7f0..be3a3caf6 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)
- 9.6291 9.6475 9.6691 9.5707 0.0422
+ 9.6675 9.6728 9.6772 9.6524 0.0108
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 c63ff7a96..7c303782e 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)
- 770.3976 770.5754 775.3952 765.2222 4.1550
+ 752.9615 755.9157 756.2220 746.7469 4.3962
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.478 seconds)
+ **Total running time of the script:** ( 1 minutes 19.575 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 2c6d98c89..4aaafa670 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
@@ -362,77 +362,31 @@ 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} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_4: Buffer(compute_3, float32, [512], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (cse_var_19 + 1)
- let cse_var_17: int32 = (cse_var_19 + 11)
- let cse_var_16: int32 = (cse_var_19 + 12)
- let cse_var_15: int32 = (cse_var_19 + 13)
- let cse_var_14: int32 = (cse_var_19 + 14)
- let cse_var_13: int32 = (cse_var_19 + 15)
- let cse_var_12: int32 = (cse_var_19 + 2)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 4)
- let cse_var_9: int32 = (cse_var_19 + 5)
- let cse_var_8: int32 = (cse_var_19 + 6)
- let cse_var_7: int32 = (cse_var_19 + 7)
- let cse_var_6: int32 = (cse_var_19 + 8)
- let cse_var_5: int32 = (cse_var_19 + 9)
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*2048)) + (i.inner*256))
- let cse_var_3: int32 = (cse_var_19 + 10)
- {
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -486,7 +440,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.861 ms
+ Execution time of this operator: 1.448 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 57bd5a61a..bbe4e97c2 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
=================
-**00:44.717** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.700** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.809**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.239**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:43.833**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.214**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.213**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.213**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.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 4ee1aa797..0795b7ba7 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: 112.01/112.01 result: MeasureResult(costs=(0.002066808103896104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8671989440917969, timestamp=1649120242.686281) [('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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.71/110.71 result: MeasureResult(costs=(0.0020911085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.795097827911377, timestamp=1649127094.2491603) [('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: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.71 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: 0x00007f2ba71a6fa2
+ 12: 0x00007fade0229fa2
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: 144.62/144.62 result: MeasureResult(costs=(0.0016008005873015872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1976046562194824, timestamp=1649120268.9132798) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 143.96/143.96 result: MeasureResult(costs=(0.00160810517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4078905582427979, timestamp=1649127120.6481802) [('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: 0.001980
+ Time cost of this operator: 0.001984
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 abbfaf914..22b9dddeb 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 311.5 98.699 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.184 1.009 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.922 0.292 (1, 1, 10, 10, 3) 1 1
- Total_time - 315.606 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.9 98.719 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.993 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.288 (1, 1, 10, 10, 3) 1 1
+ Total_time - 312.907 - - - -
@@ -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 137.8 98.091 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.76 1.253 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.922 0.656 (1, 1, 10, 10, 3) 1 1
- Total_time - 140.482 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.55 96.822 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 2.089 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 1.089 (1, 1, 10, 10, 3) 1 1
+ Total_time - 83.194 - - - -
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 2256ba875..f25e92586 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
=================
-**00:46.089** total execution time for **how_to_work_with_microtvm** files:
+**00:43.898** total execution time for **how_to_work_with_microtvm** files:
-- **00:41.816**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.647**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.207**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:39.807**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.467**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.235**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.197**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.192**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.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 4b10d03a2..facffcab9 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
=================
-**00:09.264** total execution time for **how_to_work_with_relay** files:
+**00:09.624** total execution time for **how_to_work_with_relay** files:
-- **00:07.458**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.584**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.350**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:02.060**: :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``)
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 f0bf067c3..1c03fed15 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
=================
-**00:05.833** total execution time for **how_to_work_with_schedules** files:
+**00:05.619** total execution time for **how_to_work_with_schedules** files:
-- **00:02.125**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.201**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.739**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.727**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.321**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.247**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.244**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.057**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.152**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.719**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.702**: :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``)
+- **00:00.237**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.234**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.213**: :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 36f8fdae9..13b0d5919 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -314,8 +314,8 @@ The importing needs to happen before the tensorized GEMV being executed.
B: Buffer(B_2: Pointer(float32), float32, [32768], []),
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp3mcglfu5/input0.cc'
- source_filename = "/tmp/tmp3mcglfu5/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpz3j7poeg/input0.cc'
+ source_filename = "/tmp/tmpz3j7poeg/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
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 19ad7015a..6087c3e97 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
=================
-**00:21.057** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.002** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.844**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:19.789**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
- **00:00.213**: :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 8ddf84945..33886c83b 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 22.65s!
+ resnet18_v1 inference graph built in 21.05s!
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 b2da199dd..9ad26f593 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 15.34s!
+ yolov3-tiny inference graph built in 14.58s!
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 8df6a6c5e..af946ad4b 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
=================
-**01:30.864** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.025** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.736**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:43.128**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.631**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.394**: :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 6c19b64ea..25532be6c 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
=================
-**00:03.570** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.497** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.017**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.553**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.963**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.534**: :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 5985737f6..90aa57c9b 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
=================
-**00:01.019** total execution time for **topic_vta_tutorials** files:
+**00:00.978** total execution time for **topic_vta_tutorials** files:
-- **00:00.518**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.501**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.498**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.481**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index cd7d64e31..d13b00c1d 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
+ *E
@@ -305,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.412 ms
+ Execution time of this operator: 96.048 ms
@@ -414,6 +414,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 29.080 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 4ab18a365..56863f07c 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': 499.5068872600006, 'median': 499.5384994999995, 'std': 0.6495739783797293}
+ {'mean': 492.64933207000183, 'median': 492.46404215000155, 'std': 0.7472706818090633}
@@ -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: 19.21/ 19.21 GFLOPS | Progress: (4/10) | 5.72 s
[Task 1/25] Current/Best: 9.28/ 22.76 GFLOPS | Progress: (8/10) | 9.47 s
[Task 1/25] Current/Best: 8.59/ 22.76 GFLOPS | Progress: (10/10) | 10.51 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 14.16/ 19.02 GFLOPS | Progress: (4/10) | 2.31 s
[Task 2/25] Current/Best: 14.80/ 19.02 GFLOPS | Progress: (8/10) | 3.57 s
[Task 2/25] Current/Best: 9.62/ 19.02 GFLOPS | Progress: (10/10) | 4.11 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 16.00/ 16.00 GFLOPS | Progress: (4/10) | 3.28 s
[Task 3/25] Current/Best: 6.14/ 17.13 GFLOPS | Progress: (8/10) | 5.14 s
[Task 3/25] Current/Best: 19.14/ 19.14 GFLOPS | Progress: (10/10) | 6.17 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 17.96/ 17.96 GFLOPS | Progress: (4/10) | 2.70 s
[Task 4/25] Current/Best: 15.53/ 22.00 GFLOPS | Progress: (8/10) | 4.21 s
[Task 4/25] Current/Best: 20.06/ 22.00 GFLOPS | Progress: (10/10) | 4.82 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 12.75/ 12.75 GFLOPS | Progress: (4/10) | 2.67 s
[Task 5/25] Current/Best: 12.23/ 22.32 GFLOPS | Progress: (8/10) | 4.37 s
[Task 5/25] Current/Best: 16.26/ 22.32 GFLOPS | Progress: (10/10) | 5.04 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 5.67/ 23.05 GFLOPS | Progress: (4/10) | 3.13 s
[Task 6/25] Current/Best: 3.20/ 23.05 GFLOPS | Progress: (8/10) | 5.53 s
[Task 6/25] Current/Best: 3.18/ 23.05 GFLOPS | Progress: (10/10) | 7.44 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 18.99/ 19.37 GFLOPS | Progress: (4/10) | 3.72 s
[Task 7/25] Current/Best: 15.91/ 19.37 GFLOPS | Progress: (8/10) | 6.75 s
[Task 7/25] Current/Best: 1.58/ 19.37 GFLOPS | Progress: (10/10) | 9.07 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 9.68/ 12.83 GFLOPS | Progress: (4/10) | 4.56 s
[Task 8/25] Current/Best: 16.60/ 16.60 GFLOPS | Progress: (8/10) | 16.83 s
[Task 8/25] Current/Best: 11.83/ 16.60 GFLOPS | Progress: (10/10) | 18.94 s
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 11.29/ 11.29 GFLOPS | Progress: (4/10) | 6.70 s
[Task 9/25] Current/Best: 14.36/ 14.47 GFLOPS | Progress: (8/10) | 28.84 s
[Task 9/25] Current/Best: 14.72/ 14.72 GFLOPS | Progress: (10/10) | 29.77 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 16.54/ 19.24 GFLOPS | Progress: (4/10) | 3.16 s
[Task 10/25] Current/Best: 11.37/ 19.24 GFLOPS | Progress: (8/10) | 4.66 s
[Task 10/25] Current/Best: 14.09/ 19.24 GFLOPS | Progress: (10/10) |
5.51 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 20.10/ 20.10 GFLOPS | Progress: (4/10) | 3.43 s
[Task 11/25] Current/Best: 20.24/ 20.24 GFLOPS | Progress: (8/10) | 5.31 s
[Task 11/25] Current/Best: 12.08/ 20.24 GFLOPS | Progress: (10/10) | 6.52 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 13.34/ 21.53 GFLOPS | Progress: (4/10) | 3.65 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 12.89/ 23.82 GFLOPS | Progress: (4/10) | 5.15 s
[Task 1/25] Current/Best: 6.16/ 23.82 GFLOPS | Progress: (8/10) | 7.66 s
[Task 1/25] Current/Best: 23.72/ 23.82 GFLOPS | Progress: (10/10) | 8.45 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 14.83/ 17.96 GFLOPS | Progress: (4/10) | 2.08 s
[Task 2/25] Current/Best: 5.31/ 18.40 GFLOPS | Progress: (8/10) | 3.72 s
[Task 2/25] Current/Best: 18.45/ 18.45 GFLOPS | Progress: (10/10) | 4.94 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 16.39/ 22.46 GFLOPS | Progress: (4/10) | 3.10 s
[Task 3/25] Current/Best: 15.26/ 22.46 GFLOPS | Progress: (8/10) | 5.20 s
[Task 3/25] Current/Best: 18.19/ 22.46 GFLOPS | Progress: (10/10) | 6.20 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/10) | 2.96 s
[Task 4/25] Current/Best: 15.16/ 20.84 GFLOPS | Progress: (8/10) | 4.55 s
[Task 4/25] Current/Best: 20.23/ 20.84 GFLOPS | Progress: (10/10) | 5.20 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 19.46/ 19.46 GFLOPS | Progress: (4/10) | 2.26 s
[Task 5/25] Current/Best: 16.24/ 19.46 GFLOPS | Progress: (8/10) | 5.43 s
[Task 5/25] Current/Best: 4.13/ 19.46 GFLOPS | Progress: (10/10) | 6.32 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 18.50/ 18.50 GFLOPS | Progress: (4/10) | 3.13 s
[Task 6/25] Current/Best: 14.99/ 18.50 GFLOPS | Progress: (8/10) | 6.45 s
[Task 6/25] Current/Best: 17.97/ 18.50 GFLOPS | Progress: (10/10) | 7.72 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 7.81/ 20.99 GFLOPS | Progress: (4/10) | 3.00 s
[Task 7/25] Current/Best: 18.63/ 20.99 GFLOPS | Progress: (8/10) | 5.74 s
[Task 7/25] Current/Best: 6.35/ 20.99 GFLOPS | Progress: (10/10) | 6.78 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 12.51/ 13.43 GFLOPS | Progress: (4/10) | 4.59 s
[Task 8/25] Current/Best: 11.26/ 13.43 GFLOPS | Progress: (8/10) | 10.35 s
[Task 8/25] Current/Best: 14.62/ 14.62 GFLOPS | Progress: (10/10) | 13.93 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 19.66/ 21.04 GFLOPS | Progress: (4/10) | 2.53 s
[Task 9/25] Current/Best: 23.62/ 23.62 GFLOPS | Progress: (8/10) | 3.74 s
[Task 9/25] Current/Best: 12.29/ 23.62 GFLOPS | Progress: (10/10) | 5.43 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 10.08/ 18.42 GFLOPS | Progress: (4/10) | 3.00 s
[Task 10/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (8/10) | 4.20 s
[Task 10/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (10/10) | 4.88 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 13.49/ 13.49 GFLOPS | Progress: (4/10) | 3.20 s
[Task 11/25] Current/Best: 14.59/ 21.45 GFLOPS | Progress: (8/10) | 5.13 s
[Task 11/25] Current/Best: 13.36/ 21.51 GFLOPS | Progress: (10/10) | 6.54 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 18.30/ 23.50 GFLOPS | Progress: (4/10) | 2.85 s
[Task 12/25] Current/Best: 14.50/ 23.50 GFLOPS | Progress: (8/10) | 4.60 s
[Task 12/25] Current/Best: 12.46/ 23.50 GFLOPS | Progress: (10/10) | 5.53 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 7.49/ 13.82 GFLOPS | Progress: (4/10) | 3.98 s
[Task 13/25] Current/Best: 11.17/ 18.51 GFLOPS | Progress: (8/10) | 8.50 s
[Task 13/25] Current/Best: 17.06/ 18.51 GFLOPS | Progress: (10/10) | 10.52 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (4/10) | 7.33 s
[Task 14/25] Current/Best: 11.67/ 18.38 GFLOPS | Progress: (8/10) | 13.45 s
[Task 14/25] Current/Best: 10.30/ 18.38 GFLOPS | Progress: (10/10) | 16.86 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/10) | 4.22 s
[Task 15/25] Current/Best: 12.16/ 16.94 GFLOPS | Progress: (8/10) | 8.35 s
[Task 15/25] Current/Best: 12.13/ 16.94 GFLOPS | Progress: (10/10) | 9.80 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 12/25] Current/Best: 17.85/ 21.53 GFLOPS | Progress: (8/10) | 9.67 s
[Task 12/25] Current/Best: 6.01/ 21.53 GFLOPS | Progress: (10/10) | 10.77 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 19.49/ 21.98 GFLOPS | Progress: (4/10) | 3.62 s
[Task 13/25] Current/Best: 21.10/ 21.98 GFLOPS | Progress: (8/10) | 6.07 s
[Task 13/25] Current/Best: 12.18/ 21.98 GFLOPS | Progress: (10/10) | 6.90 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 3.76/ 18.62 GFLOPS | Progress: (4/10) | 4.47 s
[Task 14/25] Current/Best: 18.19/ 18.62 GFLOPS | Progress: (8/10) | 7.97 s
[Task 14/25] Current/Best: 9.80/ 18.62 GFLOPS | Progress: (10/10) | 10.72 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 19.24/ 19.24 GFLOPS | Progress: (4/10) | 4.81 s
[Task 15/25] Current/Best: 13.74/ 22.20 GFLOPS | Progress: (8/10) | 6.32 s
[Task 15/25] Current/Best: 20.48/ 22.20 GFLOPS | Progress: (10/10) | 10.18 s Done.
-
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (4/10) | 4.36 s
[Task 16/25] Current/Best: 11.72/ 19.13 GFLOPS | Progress: (8/10) | 6.60 s
[Task 16/25] Current/Best: 1.58/ 19.13 GFLOPS | Progress: (10/10) | 7.85 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 10.93/ 17.15 GFLOPS | Progress: (4/10) | 4.60 s
[Task 17/25] Current/Best: 15.05/ 22.61 GFLOPS | Progress: (8/10) | 7.07 s
[Task 17/25] Current/Best: 17.17/ 22.61 GFLOPS | Progress: (10/10) | 8.12 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 8.59/ 20.75 GFLOPS | Progress: (4/10) | 7.99 s
[Task 18/25] Current/Best: 7.67/ 20.75 GFLOPS | Progress: (8/10) | 10.96 s
[Task 18/25] Current/Best: 15.88/ 20.75 GFLOPS | Progress: (10/10) | 12.85 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 3.09/ 19.58 GFLOPS | Progress: (4/10) | 6.66 s
[Task 19/25] Current/Best: 12.01/ 22.29 GFLOPS | Progress: (8/10) | 10.50 s
[Task 19/25] Current/Best: 10.60/ 22.29 GFLOPS | Progress: (10/10) | 11.45 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 14.57/ 18.32 GFLOPS | Progress: (4/10) | 2.79 s
[Task 20/25] Current/Best: 11.61/ 18.32 GFLOPS | Progress: (8/10) | 6.07 s
[Task 20/25] Current/Best: 11.08/ 18.32 GFLOPS | Progress: (10/10) | 6.97 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 2.73/ 18.98 GFLOPS | Progress: (4/10) | 2.73 s
[Task 21/25] Current/Best: 2.71/ 18.98 GFLOPS | Progress: (8/10) | 5.07 s
[Task 21/25] Current/Best: 14.22/ 20.19 GFLOPS | Progress: (10/10) | 5.84 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 19.70/ 19.70 GFLOPS | Progress: (4/10) | 2.40 s
[Task 22/25] Current/Best: 21.52/ 21.52 GFLOPS | Progress: (8/10) | 3.72 s
[Task 22/25] Current/Best: 17.37/ 21.52 GFLOPS | Progress: (10/10) | 4.32 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 11.93/ 11.93 GFLOPS | Progress: (4/10) | 4.04 s
[Task 23/25] Current/Best: 12.22/ 18.30 GFLOPS | Progress: (8/10) | 6.39 s
[Task 23/25] Current/Best: 17.91/ 18.30 GFLOPS | Progress: (10/10) | 7.31 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 1.95/ 8.84 GFLOPS | Progress: (4/10) | 12.73 s
[Task 24/25] Current/Best: 3.02/ 9.26 GFLOPS | Progress: (8/10) | 94.95 s
[Task 24/25] Current/Best: 9.81/ 9.81 GFLOPS | Progress: (10/10) | 100.90 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 16/25] Current/Best: 6.67/ 16.04 GFLOPS | Progress: (4/10) | 2.89 s
[Task 16/25] Current/Best: 11.77/ 16.04 GFLOPS | Progress: (8/10) | 5.17 s
[Task 16/25] Current/Best: 16.82/ 16.82 GFLOPS | Progress: (10/10) | 5.89 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 7.15/ 18.89 GFLOPS | Progress: (4/10) | 3.22 s
[Task 17/25] Current/Best: 17.56/ 18.89 GFLOPS | Progress: (8/10) | 6.35 s
[Task 17/25] Current/Best: 23.39/ 23.39 GFLOPS | Progress: (10/10) | 7.90 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 10.12/ 17.94 GFLOPS | Progress: (4/10) | 4.30 s
[Task 18/25] Current/Best: 9.77/ 18.85 GFLOPS | Progress: (8/10) | 8.22 s
[Task 18/25] Current/Best: 3.09/ 18.85 GFLOPS | Progress: (10/10) | 9.61 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 18.03/ 21.20 GFLOPS | Progress: (4/10) | 2.89 s
[Task 19/25] Current/Best: 13.94/ 21.20 GFLOPS | Progress: (8/10) | 6.95 s
[Task 19/25] Current/Best: 10.99/ 23.75 GFLOPS | Progress: (10/10) | 9.09 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 17.78/ 17.78 GFLOPS | Progress: (4/10) | 2.66 s
[Task 20/25] Current/Best: 8.05/ 17.78 GFLOPS | Progress: (8/10) | 5.83 s
[Task 20/25] Current/Best: 13.72/ 17.78 GFLOPS | Progress: (10/10) | 7.22 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 11.55/ 22.92 GFLOPS | Progress: (4/10) | 3.35 s
[Task 21/25] Current/Best: 10.45/ 22.92 GFLOPS | Progress: (8/10) | 6.43 s
[Task 21/25] Current/Best: 11.83/ 22.92 GFLOPS | Progress: (10/10) | 7.65 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 11.19/ 17.98 GFLOPS | Progress: (4/10) | 3.72 s
[Task 22/25] Current/Best: 13.56/ 17.98 GFLOPS | Progress: (8/10) | 6.16 s
[Task 22/25] Current/Best: 9.55/ 17.98 GFLOPS | Progress: (10/10) | 6.94
s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 15.78/ 15.78 GFLOPS | Progress: (4/10) | 3.46 s
[Task 23/25] Current/Best: 19.77/ 19.77 GFLOPS | Progress: (8/10) | 5.91 s
[Task 23/25] Current/Best: 19.59/ 19.77 GFLOPS | Progress: (10/10) | 7.95 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 9.02/ 9.02 GFLOPS | Progress: (4/10) | 13.04 s
[Task 24/25] Current/Best: 8.77/ 9.02 GFLOPS | Progress: (8/10) | 96.53 s
[Task 24/25] Current/Best: 3.67/ 9.02 GFLOPS | Progress: (10/10) | 129.94 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 2.98/ 9.20 GFLOPS | Progress: (4/10) | 2.80 s
[Task 25/25] Current/Best: 1.55/ 9.20 GFLOPS | Progress: (8/10) | 7.65 s
[Task 25/25] Current/Best: 1.55/ 9.20 GFLOPS | Progress: (10/10) | 110.57 s
+ Done.
+
[Task 25/25] Current/Best: 3.64/ 3.64 GFLOPS | Progress: (4/10) | 25.54 s
[Task 25/25] Current/Best: 5.68/ 5.70 GFLOPS | Progress: (8/10) | 41.91 s
[Task 25/25] Current/Best: 2.94/ 7.71 GFLOPS | Progress: (10/10) | 44.16 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': 441.3394623899967, 'median': 441.2485213499963, 'std': 1.068433134413091}
- unoptimized: {'mean': 499.5068872600006, 'median': 499.5384994999995, 'std': 0.6495739783797293}
+ optimized: {'mean': 436.79041065999854, 'median': 436.8660064999972, 'std': 0.8480162140048702}
+ unoptimized: {'mean': 492.64933207000183, 'median': 492.46404215000155, 'std': 0.7472706818090633}
@@ -669,7 +669,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 15.879 seconds)
+ **Total running time of the script:** ( 9 minutes 5.521 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 b066b2f33..d13821f57 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
- 1.286e-07 secs/op
+ 1.243e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 4af0738be..c4ff6d78f 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -230,7 +230,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xdb02f80)), stage(b, placeholder(b, 0x23baa940)), 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, 0x54663f0)), stage(b, placeholder(b, 0x4f6a0f0)), 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 b44311de0..bec29de89 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
=================
-**13:04.017** total execution time for **tutorial** files:
+**12:18.091** total execution time for **tutorial** files:
-- **10:15.879**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:02.427**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:55.027**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:26.651**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:21.776**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.067**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.739**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.230**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.056**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.056**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.055**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **09:05.521**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:29.080**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:58.970**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:25.688**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:16.499**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.266**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.711**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.203**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.041**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.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_install.py` (``install.py``)
+- **00:00.035**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index eb83e1a02..fa1746700 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -243,7 +243,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000006
@@ -436,10 +436,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.667229999697156e-06 1.0
- naive 5.8528999999999995e-06 0.7633656483803382
- parallel 6.0484e-06 0.788863774823359
- vector 2.45625e-05 3.2035689552772233
+ numpy 7.223930000463952e-06 1.0
+ naive 5.9521999999999995e-06 0.8239559352897555
+ parallel 6.2128e-06 0.8600304819677083
+ vector 2.4607699999999998e-05 3.4064145137646107
@@ -828,7 +828,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019560
+ Numpy running time: 0.018992
@@ -884,7 +884,7 @@ optimizations.
.. code-block:: none
- none: 3.466357
+ none: 3.252789
@@ -982,7 +982,7 @@ schedule.
.. code-block:: none
- blocking: 0.330141
+ blocking: 0.305186
@@ -1073,7 +1073,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.349551
+ vectorization: 0.339430
@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], []),
@@ -1144,7 +1144,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.125474
+ loop permutation: 0.116978
@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], []),
@@ -1240,7 +1240,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.109453
+ array packing: 0.110302
@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], []),
@@ -1330,7 +1330,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111336
+ block caching: 0.110856
@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], []),
@@ -1413,7 +1413,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.145616
+ parallelization: 0.144521
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1491,13 +1491,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4663571660000003 1.0
- blocking 0.33014148019999995 0.09524162236892814
- vectorization 0.3495506761 0.1008409287792359
- loop permutation 0.12547411879999998 0.03619768904102595
- array packing 0.10945300620000001 0.03157580161489914
- block caching 0.11133553360000001 0.032118886851026825
- parallelization 0.1456158214 0.04200831432729515
+ none 3.2527892347 1.0
+ blocking 0.3051860317 0.09382287313433847
+ vectorization 0.3394299146 0.10435041747526723
+ loop permutation 0.11697765680000001 0.035962261419248916
+ array packing 0.1103021563 0.03391002255028461
+ block caching 0.1108555145 0.034080140612068904
+ parallelization 0.1445205751 0.04442973850204866
@@ -1532,11 +1532,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.427 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index b33822a9c..b9a26f777 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-98580a2a0bb0de3d7f3e5b8df2c8cadc4eb05c82
+4b3b86c2c33c3c56c49afec4452a05ffbbfdc9da
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 7abed6fc3..5a1320d76 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -400,7 +400,7 @@
</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.zipb439d238-b07d-4023-a0be-b6a7a7540d22 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.zip277f5cb8-022f-41ac-b5d1-9b53b8480533 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_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 440221ee3..c945c12a0 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -463,7 +463,7 @@ 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 7.176 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.781 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 396bf5e56..aa49a433e 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -386,25 +386,9 @@ 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]
- 6%|5 | 2.50M/44.7M [00:00<00:01, 24.9MB/s]
- 11%|#1 | 5.01M/44.7M [00:00<00:01, 25.7MB/s]
- 17%|#6 | 7.46M/44.7M [00:00<00:01, 25.3MB/s]
- 22%|##2 | 9.88M/44.7M [00:00<00:01, 25.0MB/s]
- 27%|##7 | 12.3M/44.7M [00:00<00:01, 23.3MB/s]
- 32%|###2 | 14.5M/44.7M [00:00<00:01, 22.3MB/s]
- 38%|###7 | 16.9M/44.7M [00:00<00:01, 22.9MB/s]
- 43%|####2 | 19.1M/44.7M [00:00<00:01, 23.1MB/s]
- 48%|####7 | 21.3M/44.7M [00:00<00:01, 22.2MB/s]
- 53%|#####3 | 23.8M/44.7M [00:01<00:00, 23.0MB/s]
- 58%|#####8 | 26.1M/44.7M [00:01<00:00, 23.4MB/s]
- 64%|######3 | 28.4M/44.7M [00:01<00:00, 22.6MB/s]
- 69%|######8 | 30.7M/44.7M [00:01<00:00, 23.1MB/s]
- 74%|#######4 | 33.1M/44.7M [00:01<00:00, 23.5MB/s]
- 79%|#######9 | 35.5M/44.7M [00:01<00:00, 23.9MB/s]
- 85%|########4 | 37.8M/44.7M [00:01<00:00, 23.9MB/s]
- 90%|########9 | 40.1M/44.7M [00:01<00:00, 24.0MB/s]
- 95%|#########5| 42.4M/44.7M [00:01<00:00, 24.1MB/s]
-100%|##########| 44.7M/44.7M [00:01<00:00, 23.6MB/s]
+ 37%|###7 | 16.6M/44.7M [00:00<00:00, 174MB/s]
+ 87%|########7 | 39.0M/44.7M [00:00<00:00, 210MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 210MB/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 844bb5ac9..41dbbeede 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -606,7 +606,7 @@ 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 4.684 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.125 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 ebd434a71..42c412e88 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,17 +300,17 @@
<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>04:57.161</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:44.749</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:07.176</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>01:04.684</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>00:58.006</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>00:25.525</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>00:22.635</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>00:21.642</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>00:20.808</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>00:14.098</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>00:02.586</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>01:03.781</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>01:02.125</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>00:56.184</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>00:25.422</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>00:21.198</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>00:20.988</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:18.599</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>00:13.659</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>00:02.794</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 194c85159..c0121020f 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)
- 16.3039 16.3235 16.4023 16.2080 0.0673
+ 16.2752 16.2673 16.5289 16.0850 0.1057
</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 5d07f8ab5..06a9863a0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,37 +409,48 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|3 | 5.69M/170M [00:00<00:02, 59.3MB/s]
- 7%|6 | 11.3M/170M [00:00<00:03, 54.1MB/s]
- 10%|9 | 16.5M/170M [00:00<00:03, 45.3MB/s]
- 13%|#3 | 22.4M/170M [00:00<00:03, 50.8MB/s]
- 16%|#6 | 27.4M/170M [00:00<00:03, 46.4MB/s]
- 20%|#9 | 33.2M/170M [00:00<00:02, 50.4MB/s]
- 23%|##2 | 39.1M/170M [00:00<00:02, 53.8MB/s]
- 26%|##6 | 44.7M/170M [00:00<00:02, 55.3MB/s]
- 29%|##9 | 50.1M/170M [00:01<00:02, 52.5MB/s]
- 33%|###3 | 56.2M/170M [00:01<00:02, 55.9MB/s]
- 37%|###6 | 62.0M/170M [00:01<00:01, 57.4MB/s]
- 40%|###9 | 67.6M/170M [00:01<00:01, 56.9MB/s]
- 43%|####3 | 73.1M/170M [00:01<00:01, 56.1MB/s]
- 46%|####6 | 78.4M/170M [00:01<00:01, 49.3MB/s]
- 49%|####9 | 84.1M/170M [00:01<00:01, 51.8MB/s]
- 53%|#####3 | 90.6M/170M [00:01<00:01, 56.5MB/s]
- 57%|#####6 | 96.2M/170M [00:01<00:01, 56.4MB/s]
- 60%|#####9 | 102M/170M [00:02<00:01, 53.1MB/s]
- 63%|######3 | 108M/170M [00:02<00:01, 55.4MB/s]
- 66%|######6 | 113M/170M [00:02<00:01, 55.5MB/s]
- 70%|######9 | 118M/170M [00:02<00:00, 55.5MB/s]
- 73%|#######2 | 124M/170M [00:02<00:00, 55.6MB/s]
- 76%|#######5 | 129M/170M [00:02<00:00, 55.2MB/s]
- 79%|#######9 | 134M/170M [00:02<00:00, 48.2MB/s]
- 82%|########1 | 139M/170M [00:02<00:00, 45.2MB/s]
- 85%|########4 | 144M/170M [00:02<00:00, 48.2MB/s]
- 88%|########7 | 149M/170M [00:02<00:00, 49.5MB/s]
- 91%|#########1| 155M/170M [00:03<00:00, 52.7MB/s]
- 94%|#########4| 160M/170M [00:03<00:00, 52.3MB/s]
- 97%|#########7| 165M/170M [00:03<00:00, 51.5MB/s]
-100%|##########| 170M/170M [00:03<00:00, 51.7MB/s]
+ 1%|1 | 2.25M/170M [00:00<00:07, 22.5MB/s]
+ 3%|3 | 5.12M/170M [00:00<00:06, 26.4MB/s]
+ 6%|5 | 9.80M/170M [00:00<00:04, 36.5MB/s]
+ 8%|7 | 13.4M/170M [00:00<00:04, 36.7MB/s]
+ 10%|# | 17.5M/170M [00:00<00:04, 39.1MB/s]
+ 13%|#2 | 21.6M/170M [00:00<00:03, 40.3MB/s]
+ 15%|#5 | 25.7M/170M [00:00<00:03, 41.0MB/s]
+ 17%|#7 | 29.7M/170M [00:00<00:04, 34.6MB/s]
+ 20%|#9 | 33.4M/170M [00:00<00:04, 35.6MB/s]
+ 22%|##1 | 36.9M/170M [00:01<00:04, 30.2MB/s]
+ 24%|##3 | 40.4M/170M [00:01<00:04, 31.7MB/s]
+ 26%|##5 | 43.5M/170M [00:01<00:04, 29.5MB/s]
+ 28%|##8 | 47.6M/170M [00:01<00:03, 32.8MB/s]
+ 30%|### | 51.7M/170M [00:01<00:03, 35.5MB/s]
+ 33%|###2 | 55.2M/170M [00:01<00:03, 34.7MB/s]
+ 35%|###4 | 59.4M/170M [00:01<00:03, 35.6MB/s]
+ 37%|###7 | 62.8M/170M [00:01<00:03, 35.2MB/s]
+ 39%|###9 | 67.0M/170M [00:02<00:02, 37.5MB/s]
+ 42%|####1 | 70.6M/170M [00:02<00:02, 37.4MB/s]
+ 44%|####3 | 74.2M/170M [00:02<00:02, 35.0MB/s]
+ 46%|####5 | 77.6M/170M [00:02<00:03, 31.4MB/s]
+ 49%|####8 | 82.6M/170M [00:02<00:02, 35.2MB/s]
+ 51%|##### | 86.0M/170M [00:02<00:02, 34.1MB/s]
+ 53%|#####2 | 89.3M/170M [00:02<00:02, 32.3MB/s]
+ 55%|#####4 | 93.0M/170M [00:02<00:02, 33.9MB/s]
+ 57%|#####7 | 97.2M/170M [00:02<00:02, 36.8MB/s]
+ 60%|#####9 | 101M/170M [00:03<00:01, 37.8MB/s]
+ 62%|######2 | 106M/170M [00:03<00:01, 41.4MB/s]
+ 65%|######5 | 111M/170M [00:03<00:01, 44.7MB/s]
+ 68%|######7 | 115M/170M [00:03<00:01, 42.6MB/s]
+ 70%|####### | 120M/170M [00:03<00:01, 37.6MB/s]
+ 73%|#######2 | 123M/170M [00:03<00:01, 36.6MB/s]
+ 76%|#######5 | 129M/170M [00:03<00:01, 42.3MB/s]
+ 78%|#######8 | 133M/170M [00:03<00:00, 41.5MB/s]
+ 81%|########1 | 138M/170M [00:03<00:00, 43.5MB/s]
+ 84%|########3 | 143M/170M [00:04<00:00, 44.9MB/s]
+ 87%|########6 | 147M/170M [00:04<00:00, 45.5MB/s]
+ 89%|########9 | 152M/170M [00:04<00:00, 44.7MB/s]
+ 92%|#########2| 156M/170M [00:04<00:00, 45.6MB/s]
+ 95%|#########4| 161M/170M [00:04<00:00, 41.0MB/s]
+ 98%|#########7| 166M/170M [00:04<00:00, 44.6MB/s]
+100%|##########| 170M/170M [00:04<00:00, 37.9MB/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').
@@ -532,7 +543,7 @@ 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 15.666 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.160 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 435555764..42728e328 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,9 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 205MB/s]
+ 36%|###5 | 4.83M/13.6M [00:00<00:00, 50.6MB/s]
+ 74%|#######3 | 9.99M/13.6M [00:00<00:00, 52.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 40.5MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +541,7 @@ 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)
- 90.6596 90.4672 96.6449 90.2357 0.8152
+ 90.1404 90.0909 90.8977 89.9211 0.1899
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +580,7 @@ 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 7.434 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.147 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 71742d61d..dca087cdd 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)
- 120.0871 119.9965 128.7969 119.2630 0.9346
+ 120.8911 120.9887 127.1042 118.9195 1.0356
</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 54.477 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.531 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 11dcba386..b047beb3d 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 13.899 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.123 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 52c8cc2ad..dbba5480a 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,35 +415,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 0%| | 323/132723 [00:00<00:44, 2950.93KB/s]
- 1%|1 | 1606/132723 [00:00<00:15, 8543.58KB/s]
- 2%|2 | 3076/132723 [00:00<00:11, 10822.33KB/s]
- 5%|5 | 6859/132723 [00:00<00:05, 21074.39KB/s]
- 8%|7 | 10318/132723 [00:00<00:04, 25823.47KB/s]
- 11%|#1 | 14785/132723 [00:00<00:03, 32122.89KB/s]
- 14%|#3 | 18035/132723 [00:00<00:05, 22823.67KB/s]
- 16%|#5 | 21063/132723 [00:00<00:04, 24639.01KB/s]
- 18%|#7 | 23833/132723 [00:01<00:04, 23625.71KB/s]
- 20%|#9 | 26406/132723 [00:01<00:04, 24074.79KB/s]
- 22%|##1 | 29104/132723 [00:01<00:04, 24795.63KB/s]
- 24%|##3 | 31701/132723 [00:01<00:04, 22995.87KB/s]
- 26%|##5 | 34136/132723 [00:01<00:04, 23347.37KB/s]
- 30%|### | 40459/132723 [00:01<00:02, 34303.66KB/s]
- 34%|###3 | 45117/132723 [00:01<00:02, 37762.67KB/s]
- 39%|###9 | 52273/132723 [00:01<00:01, 47462.17KB/s]
- 43%|####3 | 57162/132723 [00:01<00:01, 42813.06KB/s]
- 48%|####7 | 63450/132723 [00:02<00:01, 48113.90KB/s]
- 52%|#####1 | 68748/132723 [00:02<00:01, 49316.90KB/s]
- 57%|#####7 | 75823/132723 [00:02<00:01, 55401.37KB/s]
- 61%|######1 | 81493/132723 [00:02<00:01, 47677.35KB/s]
- 66%|######5 | 87110/132723 [00:02<00:00, 49574.97KB/s]
- 71%|#######1 | 94391/132723 [00:02<00:00, 55846.37KB/s]
- 76%|#######5 | 100566/132723 [00:02<00:00, 57473.23KB/s]
- 80%|######## | 106480/132723 [00:02<00:00, 50895.46KB/s]
- 86%|########6 | 114296/132723 [00:02<00:00, 58065.84KB/s]
- 92%|#########2| 122288/132723 [00:03<00:00, 64033.68KB/s]
- 98%|#########8| 130312/132723 [00:03<00:00, 68580.22KB/s]
-100%|##########| 132723/132723 [00:03<00:00, 41515.10KB/s]
+ 6%|5 | 7302/132723 [00:00<00:01, 73010.15KB/s]
+ 11%|#1 | 15153/132723 [00:00<00:01, 76242.22KB/s]
+ 18%|#8 | 24070/132723 [00:00<00:01, 82140.31KB/s]
+ 25%|##4 | 32988/132723 [00:00<00:01, 84913.76KB/s]
+ 32%|###1 | 41907/132723 [00:00<00:01, 86452.58KB/s]
+ 38%|###8 | 50875/132723 [00:00<00:00, 87547.79KB/s]
+ 45%|####4 | 59630/132723 [00:00<00:00, 85505.68KB/s]
+ 52%|#####1 | 68568/132723 [00:00<00:00, 86717.34KB/s]
+ 58%|#####8 | 77514/132723 [00:00<00:00, 87561.81KB/s]
+ 65%|######5 | 86495/132723 [00:01<00:00, 88248.92KB/s]
+ 72%|#######1 | 95448/132723 [00:01<00:00, 88636.20KB/s]
+ 79%|#######8 | 104397/132723 [00:01<00:00, 88891.45KB/s]
+ 85%|########5 | 113289/132723 [00:01<00:00, 88700.82KB/s]
+ 92%|#########2| 122162/132723 [00:01<00:00, 86876.44KB/s]
+ 99%|#########8| 131146/132723 [00:01<00:00, 87752.51KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 86484.10KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -483,7 +470,7 @@ 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 30.263 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.164 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 5807c8121..70325fd90 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>10:53.626</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:26.596</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:15.666</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>02:30.263</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>01:54.477</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>01:13.899</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>01:07.434</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>00:29.638</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>00:22.040</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>00:00.209</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>03:07.160</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:22.164</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>01:53.531</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>01:10.123</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>01:04.147</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>00:27.806</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>00:21.473</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>00:00.190</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 332fbfdc2..496c643ea 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.zip512378da-3ab2-41df-9630-50b8ac086852 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.zipb90e6efb-e55e-4645-a72d-25f8fd8621df 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 e9d59dadf..162480dbc 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>00:39.696</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.934</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:36.013</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>00:02.373</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>00:01.096</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>00:00.215</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>00:34.425</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>00:02.238</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>00:01.070</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>00:00.201</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 f1d80fffd..9938bb167 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: 6200us [6200us] (45.58%; 45.58%)
-FoldScaleAxis: 7401us [3us] (54.42%; 54.42%)
- FoldConstant: 7398us [1573us] (54.40%; 99.96%)
- InferType: 5826us [5826us] (42.83%; 78.74%)
+InferType: 6232us [6232us] (45.04%; 45.04%)
+FoldScaleAxis: 7605us [2us] (54.96%; 54.96%)
+ FoldConstant: 7603us [1520us] (54.95%; 99.97%)
+ InferType: 6083us [6083us] (43.96%; 80.01%)
</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: 5979us [5979us] (45.02%; 45.02%)
-FoldScaleAxis: 7302us [3us] (54.98%; 54.98%)
- FoldConstant: 7300us [1515us] (54.96%; 99.96%)
- InferType: 5785us [5785us] (43.56%; 79.25%)
+InferType: 6067us [6067us] (45.38%; 45.38%)
+FoldScaleAxis: 7304us [2us] (54.62%; 54.62%)
+ FoldConstant: 7302us [1515us] (54.61%; 99.97%)
+ InferType: 5787us [5787us] (43.28%; 79.25%)
</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 e4c83b5df..a7a975b4d 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: 54.140382 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 47.607634 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 afc8416de..ef1845e12 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -876,7 +876,7 @@ 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: 8.963553 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.836040 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 43d11cbae..989cb1b9b 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: 0.019616
-Baseline: 3.454113
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019144
+Baseline: 3.251305
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -493,7 +493,7 @@ 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: 0.325970
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300639
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -561,7 +561,7 @@ 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: 0.344127
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.334595
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
</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: 0.122029
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117366
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -707,7 +707,7 @@ 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: 0.111398
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111272
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -794,7 +794,7 @@ 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: 0.111851
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111764
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -885,7 +885,7 @@ 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: 0.146843
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144907
</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 2d5a2dd44..ee572946d 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>00:35.940</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.601</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:33.232</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>00:01.448</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>00:01.260</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>00:31.963</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>00:01.407</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 f48bec2ae..7c14cc2b5 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>05:11.520</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:01.031</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:22.939</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>01:21.478</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>00:41.566</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>00:27.796</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>00:09.017</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>00:08.724</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>02:28.365</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>01:19.575</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>00:40.499</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>00:15.752</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>00:08.590</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>00:08.249</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 06c813c7e..70c265293 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
@@ -469,1139 +469,667 @@ cooperative fetching, unrolling and operator fusion.</p>
bias: Buffer(bias_2: Pointer(float32), float32, [512], []),
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [576]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[13] = 0f32
- for (rc.outer.outer: int32, 0, 64) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [1]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [4032]), 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" = 784 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
+ for (rc.outer.outer: int32, 0, 8) {
+ let cse_var_2: int32 = (rc.outer.outer*3136)
+ let cse_var_1: int32 = (rc.outer.outer*576)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[(threadIdx.x_1*12)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod((threadIdx.x_1*12), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod((threadIdx.x_1*12), 9)) [...]
- pad_temp.shared_1[((threadIdx.x_1*12) + 1)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod(((threadIdx.x_1*12) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 2)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1*4), 27)) && (floormod(((threadIdx.x_1*12) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 3)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 4)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 5)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 1), 27)) && (floormod(((threadIdx.x_1*12) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 1), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 1), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 6)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 6), 9))) && (floormod(((threadIdx.x_1*12) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 7)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 7), 9))) && (floormod(((threadIdx.x_1*12) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 8)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 2), 27)) && (floormod(((threadIdx.x_1*12) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 8), 9))) && (floormod(((threadIdx.x_1*12) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 2), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 2), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod((threadIdx.x_1*12), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*12) + 10)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8)], 0f [...]
- pad_temp.shared_1[((threadIdx.x_1*12) + 11)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8)], 0f [...]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [4032], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28 {
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 336)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 3), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 337)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 4), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 338)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 112), 27)) && (floormod(((threadIdx.x_1*12) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 112), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 112), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 5), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 339)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 6), 9))) && (floormod(((threadIdx.x_1*12) + 6), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 6), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 340)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 16), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 7), 9))) && (floormod(((threadIdx.x_1*12) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 7), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 341)] = @tir.if_then_else(((((3 <= floormod(((threadIdx.x_1*4) + 113), 27)) && (floormod(((threadIdx.x_1*12) + 17), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 8), 9))) && (floormod(((threadIdx.x_1*12) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 113), 27)*49)) + (floordiv(floormod(((threadIdx.x_1*4) + 113), 27), 3)*7)) + floormod(((threadIdx.x_1*12) + 8), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 342)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 18), 81) < 72)) && (1 <= floormod((threadIdx.x_1*12), 9))) && (floormod((threadIdx.x_1*12), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod((threadIdx.x_1*12), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 343)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 19), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 1), 9))) && (floormod(((threadIdx.x_1*12) + 1), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*12) + 1), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 344)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)) && (floormod(((threadIdx.x_1*12) + 20), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 2), 9))) && (floormod(((threadIdx.x_1*12) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 114), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 2), 9)*7)) + floormod(((threadIdx.x_1*12) + 2), 9)) - 8) [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 345)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 21), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 3), 9))) && (floormod(((threadIdx.x_1*12) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 346)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 22), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 4), 9))) && (floormod(((threadIdx.x_1*12) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12 [...]
- }
- if @tir.likely((threadIdx.x_1 < 26), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*12) + 347)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)) && (floormod(((threadIdx.x_1*12) + 23), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*12) + 5), 9))) && (floormod(((threadIdx.x_1*12) + 5), 9) < 8)), data[((((cse_var_2 + (floordiv(((threadIdx.x_1*4) + 115), 27)*49)) + (floormod((floordiv(((threadIdx.x_1*4) + 112), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12 [...]
- }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3))]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1: Buffer(kernel.shared, float32, [576], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 28)] = kernel[(((blockIdx.x*36864) + cse_var_1) + (threadIdx.x_2 + 28))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 68), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 52), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 36), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
- 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), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 364)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 91), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 420)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 105), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 60), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 476)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 119), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 44), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 504)] = kernel[((((blockIdx.x*36864) + cse_var_1) + threadIdx.x_2) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- kernel.shared_1[(threadIdx.x_2 + 532)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 133), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 72))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 28;
- if @tir.likely((threadIdx.x_2 < 16), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((blockIdx.x*36864) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else(((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[floormod(threadIdx.x, 7)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[(floordiv(threadIdx.x, 7)*72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 72)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 300)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 108)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 117)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 135)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 144)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 153)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 303)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 18)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 21)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 198)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 207)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 216)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 225)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 24)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 234)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 27)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 30)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 270)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 279)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 288)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 297)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 306)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 33)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 289)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 292)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 28)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 37)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 46)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 55)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 64)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 73)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 295)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 298)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 301)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 109)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 118)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 127)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 136)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 145)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 16)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 154)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 304)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 19)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 307)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 22)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 310)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 190)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 199)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 208)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 217)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 226)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 25)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 235)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 313)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 28)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 316)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 31)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 319)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 271)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 280)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 289)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 298)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 307)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 34)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 316)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 322)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 290)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 293)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 29)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 38)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 47)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 56)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 65)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 74)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 296)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 299)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 302)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 110)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 119)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 128)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 137)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 146)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 17)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 155)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 305)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 20)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 308)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 23)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 311)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 191)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 200)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 209)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 218)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 227)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 26)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 236)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 314)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 29)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 317)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 320)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 272)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 281)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 290)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 299)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 308)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 35)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 317)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 323)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 36)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 39)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 351)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 360)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 369)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 387)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 42)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 396)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 45)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 48)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 432)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 450)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 459)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 468)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 51)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 477)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 54)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 57)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 513)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 522)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 531)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 540)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 549)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 60)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 558)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 63)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 66)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 594)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 603)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 612)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 621)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 69)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 639)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 37)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 325)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 40)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 328)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 352)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 361)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 370)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 379)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 388)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 43)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 397)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 331)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 46)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 334)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 49)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 337)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 433)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 442)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 451)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 460)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 469)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 52)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 478)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 340)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 55)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 343)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 58)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 346)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 514)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 523)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 532)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 541)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 550)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 61)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 559)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 349)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 64)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 352)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 67)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 355)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 595)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 604)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 613)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 622)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 631)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 70)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 640)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 358)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 38)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 326)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 41)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 329)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 353)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 362)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 371)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 380)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 389)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 44)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 398)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 332)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 47)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 335)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 50)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 338)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 434)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 443)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 452)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 461)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 470)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 53)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 479)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 341)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 56)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 344)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 59)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 347)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 515)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 524)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 533)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 542)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 551)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 62)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 560)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 350)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 65)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 353)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 68)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 356)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 596)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 605)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 614)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 623)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 632)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 71)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(floormod(threadIdx.x, 7) + 641)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*72) + 359)]))
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + 1)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + 1)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + floormod(threadIdx.x_1, 63)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 4), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 4), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 112), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 4), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 8), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 8), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 224), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 8), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 336), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ pad_temp.shared_1[(threadIdx.x_1 + 3136)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 448), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_1 < 112), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 3920)] = @tir.if_then_else((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 2), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 2), 9) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 560), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 2), 9)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[threadIdx.x_2] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 192)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 49), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 98), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 32), 192)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 784;
+ if @tir.likely((threadIdx.x_2 < 720), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 16) + 147), 12)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 48), 192)*3)) + 2)]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[floormod(threadIdx.x, 49)]*kernel.shared_1[(floordiv(threadIdx.x, 49)*192)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 7)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 14)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 63)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 70)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 77)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 126)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 133)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 140)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 189)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 196)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 203)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 259)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 266)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 315)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 322)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 329)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 378)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 385)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 392)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 441)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 448)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 455)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 511)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 518)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 574)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 581)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 630)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 637)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 644)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 693)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 700)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 707)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 756)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 763)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 770)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 826)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 833)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 882)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 889)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 896)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 945)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 952)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 959)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1008)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1015)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1022)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1078)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1085)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1141)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1148)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1197)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1204)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1211)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1260)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1267)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1274)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1323)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1330)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1337)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1386)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1393)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1400)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1449)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1456)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1463)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1512)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1519)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1526)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1575)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1582)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1589)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1638)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1645)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1652)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1701)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1708)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1715)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1764)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1771)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1778)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1827)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1834)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1841)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1890)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1897)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1904)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1953)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1960)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 1967)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 95)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2016)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2023)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 97)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2030)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 98)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2079)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 99)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2086)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 100)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2093)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 101)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2142)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 102)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2149)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 103)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2156)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 104)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2205)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 105)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2212)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 106)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2219)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2268)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 108)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2275)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 109)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2282)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 110)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2331)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 111)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2338)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 112)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2345)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 113)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2394)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 114)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2401)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 115)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2408)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 116)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2457)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 117)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2464)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 118)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2471)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 119)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2520)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 120)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2527)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 121)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2534)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 122)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2583)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 123)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2590)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 124)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2597)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 125)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2646)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 126)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2653)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 127)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2660)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 128)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2709)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 129)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2716)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 130)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2723)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 131)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2772)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 132)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2779)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 133)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2786)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 134)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2835)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 135)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2842)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 136)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2849)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 137)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2898)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 138)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2905)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 139)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2912)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 140)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2961)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 141)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2968)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 142)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 2975)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 143)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3024)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3031)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 145)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3038)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 146)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3087)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 147)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3094)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 148)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 149)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3150)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 150)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3157)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 151)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3213)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3220)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3227)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 155)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3276)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 156)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3283)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 157)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3290)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 158)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3339)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 159)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3346)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 160)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3353)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3402)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3409)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 164)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3465)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 165)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3472)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 166)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3479)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 167)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3528)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 168)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3535)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 169)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3542)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3591)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3598)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3605)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 173)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3654)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 174)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3661)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 175)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 176)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3717)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 177)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3724)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 178)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3780)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3787)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3794)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 182)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3843)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 183)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3850)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 184)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3857)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 185)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3906)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 186)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3913)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 187)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3920)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3969)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3976)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(floormod(threadIdx.x, 49) + 3983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*192) + 191)]))
}
}
- for (i2.inner: int32, 0, 7) {
- compute[((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((blockIdx.x*8) + floordiv(threadIdx.x, 7))]), 0f32)
- compute[(((((blockIdx.x*392) + (floordiv(threadIdx.x, 7)*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7)) + 196)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((blockIdx.x*8) + floordiv(threadIdx.x, 7)) + 4)]), 0f32)
- }
+ compute[((blockIdx.x*784) + threadIdx.x)] = max((conv2d_nchw_1[0] + bias[((blockIdx.x*16) + floordiv(threadIdx.x, 49))]), 0f32)
}
}
</pre></div>
@@ -1638,7 +1166,7 @@ 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: 0.213 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.389 ms
</pre></div>
</div>
</div>
@@ -1670,31 +1198,31 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=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_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+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=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -1717,12 +1245,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=784)
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=12)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=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=784)
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, "unroll_explicit", True)
@@ -1742,1111 +1270,638 @@ 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) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[576];
+extern "C" __global__ void __launch_bounds__(784) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[1];
+ __shared__ float pad_temp_shared[4032];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int rc_outer_outer = 0; rc_outer_outer < 8; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 12)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && (((((int)threadIdx.x) * 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 1)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && ((((((int)threadIdx.x) * 12) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 2)] = (((((3 <= ((((int)threadIdx.x) * 4) % 27)) && ((((((int)threadIdx.x) * 12) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 27) * 49)) + ((((((int)threadIdx.x) * 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 3)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 4)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 5)] = (((((3 <= (((((int)threadIdx.x) * 4) + 1) % 27)) && ((((((int)threadIdx.x) * 12) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 1) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 6)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 6) % 9))) && ((((((int)threadIdx.x) * 12) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 7)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 7) % 9))) && ((((((int)threadIdx.x) * 12) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 8)] = (((((3 <= (((((int)threadIdx.x) * 4) + 2) % 27)) && ((((((int)threadIdx.x) * 12) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 8) % 9))) && ((((((int)threadIdx.x) * 12) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 2) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 10)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 12) + 11)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 336)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 337)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 338)] = (((((3 <= (((((int)threadIdx.x) * 4) + 4) % 27)) && ((((((int)threadIdx.x) * 12) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 112) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 4) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 339)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 6) % 9))) && ((((((int)threadIdx.x) * 12) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 340)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 16) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 7) % 9))) && ((((((int)threadIdx.x) * 12) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = ((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 341)] = (((((3 <= (((((int)threadIdx.x) * 4) + 5) % 27)) && ((((((int)threadIdx.x) * 12) + 17) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 8) % 9))) && ((((((int)threadIdx.x) * 12) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 113) / 27) * 49)) + (((((((int)threadIdx.x) * 4) + 5) % 27) / 3) * 7)) + (((((int)threadIdx.x) * 12) + 8) % 9)) - 8)] : 0.000000e+00f);
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3))];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3))];
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 342)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 18) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 12) % 9))) && (((((int)threadIdx.x) * 12) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + ((((int)threadIdx.x) * 12) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 343)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 19) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 1) % 9))) && ((((((int)threadIdx.x) * 12) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 344)] = (((((1 <= ((((((int)threadIdx.x) * 4) / 3) + 2) % 9)) && ((((((int)threadIdx.x) * 12) + 20) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 2) % 9))) && ((((((int)threadIdx.x) * 12) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 114) / 27) * 49)) + (((((((int)threadIdx.x) * 4) / 3) + 2) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 345)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 21) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 3) % 9))) && ((((((int)threadIdx.x) * 12) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 3) % 9)) - [...]
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = (((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = (((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 346)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 22) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 4) % 9))) && ((((((int)threadIdx.x) * 12) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 4) % 9)) - [...]
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + 1)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + 1)];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + 1)];
}
- if (((int)threadIdx.x) < 26) {
- pad_temp_shared[((((int)threadIdx.x) * 12) + 347)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9)) && ((((((int)threadIdx.x) * 12) + 23) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 12) + 5) % 9))) && ((((((int)threadIdx.x) * 12) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 115) / 27) * 49)) + ((((((((int)threadIdx.x) * 4) + 112) / 3) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 12) + 5) % 9)) - [...]
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = ((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((rc_outer_outer * 3136) + ((((int)threadIdx.x) / 63) * 49)) + (((int)threadIdx.x) % 63)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = ((((1 <= (((((int)threadIdx.x) / 7) + 4) % 9)) && ((((((int)threadIdx.x) / 7) + 4) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 784) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 4) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1568)] = ((((1 <= (((((int)threadIdx.x) / 7) + 8) % 9)) && ((((((int)threadIdx.x) / 7) + 8) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 1568) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 8) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 2352)] = ((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 2352) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 3136)] = ((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3136) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 112) {
+ pad_temp_shared[(((int)threadIdx.x) + 3920)] = ((((1 <= (((((int)threadIdx.x) / 7) + 2) % 9)) && ((((((int)threadIdx.x) / 7) + 2) % 9) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[(((((rc_outer_outer * 3136) + (((((int)threadIdx.x) + 3920) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 2) % 9) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 28)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 28)];
- kernel_shared[(((int)threadIdx.x) + 56)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 56) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
- kernel_shared[(((int)threadIdx.x) + 84)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 84) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 12))];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
- kernel_shared[(((int)threadIdx.x) + 140)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 140) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 68) % 72))];
- kernel_shared[(((int)threadIdx.x) + 168)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 168) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 52) % 72))];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
- kernel_shared[(((int)threadIdx.x) + 252)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 252) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 36))];
- kernel_shared[(((int)threadIdx.x) + 280)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
- kernel_shared[(((int)threadIdx.x) + 308)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 308) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 20))];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 336) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
- kernel_shared[(((int)threadIdx.x) + 364)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 364) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 4))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
- kernel_shared[(((int)threadIdx.x) + 420)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 420) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 60) % 72))];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
- kernel_shared[(((int)threadIdx.x) + 476)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 476) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 44))];
- kernel_shared[(((int)threadIdx.x) + 504)] = kernel[((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 532)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 532) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 28))];
- if (((int)threadIdx.x) < 16) {
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 56))];
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 192) * 4608)) + (rc_outer_outer * 576)) + ((((int)threadIdx.x) % 192) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 16) % 192) * 3)) + 2)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 32) % 192) * 3)) + 2)];
+ if (((int)threadIdx.x) < 720) {
+ kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 192) * 4608)) + (rc_outer_outer * 576)) + (((((int)threadIdx.x) + 48) % 192) * 3)) + 2)];
}
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((int)threadIdx.x) % 7)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[((((int)threadIdx.x) / 7) * 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 63)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 72)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 81)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 90)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 300)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 99)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 108)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 117)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 126)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 135)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 144)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 153)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 303)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 162)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 18)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 171)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 21)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 180)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 189)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 198)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 207)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 216)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 225)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 24)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 234)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 243)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 27)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 252)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 30)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 261)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 270)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 279)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 288)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 297)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 306)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 33)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 315)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 1)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 289)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 10)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 292)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 19)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 28)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 37)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 46)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 55)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 64)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 73)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 295)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 82)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 298)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 91)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 301)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 100)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 109)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 118)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 127)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 136)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 145)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 16)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 154)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 304)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 163)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 19)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 307)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 172)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 22)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 310)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 181)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 190)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 199)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 208)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 217)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 226)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 25)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 235)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 313)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 244)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 28)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 316)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 253)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 31)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 319)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 262)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 271)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 280)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 289)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 298)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 307)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 34)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 316)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 322)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 2)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 290)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 11)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 293)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 20)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 29)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 38)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 47)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 56)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 65)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 74)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 296)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 83)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 299)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 92)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 302)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 101)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 110)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 119)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 128)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 137)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 146)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 17)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 155)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 305)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 164)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 20)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 308)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 173)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 23)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 311)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 182)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 191)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 200)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 209)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 218)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 227)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 26)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 236)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 314)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 245)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 29)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 317)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 254)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 320)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 263)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 272)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 281)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 290)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 299)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 308)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 35)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 317)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 323)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 324)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 36)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 333)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 39)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 342)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 351)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 360)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 369)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 378)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 387)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 42)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 396)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 405)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 45)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 414)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 48)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 423)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 432)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 441)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 450)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 459)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 468)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 51)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 477)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 486)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 54)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 495)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 57)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 504)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 513)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 522)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 531)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 540)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 549)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 60)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 558)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 567)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 63)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 576)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 66)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 585)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 594)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 603)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 612)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 621)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 630)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 69)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 639)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 325)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 37)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 325)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 334)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 40)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 328)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 343)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 352)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 361)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 370)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 379)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 388)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 43)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 397)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 331)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 406)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 46)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 334)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 415)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 49)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 337)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 424)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 433)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 442)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 451)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 460)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 469)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 52)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 478)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 340)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 487)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 55)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 343)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 496)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 58)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 346)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 505)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 514)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 523)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 532)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 541)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 550)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 61)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 559)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 349)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 568)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 64)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 352)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 577)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 67)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 355)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 586)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 595)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 604)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 613)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 622)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 631)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 70)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 640)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 358)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 326)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 38)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 326)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 335)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 41)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 329)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 344)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 353)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 362)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 371)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 380)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 389)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 44)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 398)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 332)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 407)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 47)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 335)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 416)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 50)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 338)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 425)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 434)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 443)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 452)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 461)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 470)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 53)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 479)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 341)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 488)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 56)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 344)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 497)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 59)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 347)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 506)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 515)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 524)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 533)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 542)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 551)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 62)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 560)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 350)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 569)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 65)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 353)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 578)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 68)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 356)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 587)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 596)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 605)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 614)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 623)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 632)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 71)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((int)threadIdx.x) % 7) + 641)] * kernel_shared[(((((int)threadIdx.x) / 7) * 72) + 359)]));
- }
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7))]), 0.000000e+00f);
- compute[(((((((int)blockIdx.x) * 392) + ((((int)threadIdx.x) / 7) * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7)) + 196)] = max((conv2d_nchw[(i2_inner + 7)] + bias[(((((int)blockIdx.x) * 8) + (((int)threadIdx.x) / 7)) + 4)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((int)threadIdx.x) % 49)] * kernel_shared[((((int)threadIdx.x) / 49) * 192)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 7)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 14)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 63)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 70)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 77)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 126)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 133)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 140)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 189)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 196)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 203)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 259)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 266)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 315)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 322)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 329)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 378)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 385)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 392)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 441)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 448)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 455)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 511)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 518)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 574)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 581)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 630)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 637)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 644)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 693)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 700)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 707)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 756)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 763)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 770)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 826)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 833)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 882)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 889)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 896)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 945)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 952)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 959)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1008)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1015)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1022)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1078)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1085)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1141)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1148)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1197)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1204)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1211)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1260)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1267)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1274)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1323)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1330)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1337)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1386)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1393)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1400)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1449)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1456)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1463)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1512)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1519)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1526)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1575)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1582)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1589)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1638)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1645)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1652)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1701)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1708)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1715)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1764)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1771)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1778)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1827)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1834)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1841)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1890)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1897)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1904)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1953)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1960)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 1967)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 95)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2016)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2023)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 97)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2030)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 98)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2079)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 99)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2086)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 100)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2093)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 101)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2142)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 102)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2149)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 103)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2156)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 104)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2205)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 105)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2212)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 106)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2219)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2268)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 108)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2275)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 109)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2282)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 110)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2331)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 111)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2338)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 112)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2345)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 113)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2394)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 114)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2401)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 115)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2408)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 116)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2457)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 117)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2464)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 118)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2471)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 119)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2520)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 120)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2527)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 121)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2534)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 122)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2583)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 123)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2590)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 124)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2597)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 125)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2646)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 126)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2653)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 127)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2660)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 128)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2709)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 129)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2716)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 130)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2723)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 131)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2772)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 132)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2779)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 133)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2786)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 134)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2835)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 135)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2842)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 136)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2849)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 137)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2898)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 138)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2905)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 139)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2912)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 140)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2961)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 141)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2968)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 142)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 2975)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 143)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3024)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3031)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 145)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3038)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 146)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3087)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 147)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3094)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 148)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 149)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3150)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 150)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3157)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 151)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3213)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3220)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3227)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 155)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3276)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 156)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3283)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 157)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3290)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 158)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3339)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 159)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3346)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 160)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3353)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3402)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3409)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 164)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3465)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 165)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3472)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 166)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3479)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 167)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3528)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 168)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3535)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 169)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3542)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3591)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3598)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3605)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 173)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3654)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 174)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3661)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 175)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 176)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3717)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 177)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3724)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 178)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3780)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3787)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3794)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 182)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3843)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 183)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3850)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 184)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3857)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 185)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3906)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 186)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3913)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 187)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3920)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3969)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3976)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((int)threadIdx.x) % 49) + 3983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 192) + 191)]));
}
+ compute[((((int)blockIdx.x) * 784) + ((int)threadIdx.x))] = max((conv2d_nchw[0] + bias[((((int)blockIdx.x) * 16) + (((int)threadIdx.x) / 49))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -2883,7 +1938,7 @@ 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 22.939 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 28.365 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 b1a6b7114..89dbf2d4a 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)
- 9.6291 9.6475 9.6691 9.5707 0.0422
+ 9.6675 9.6728 9.6772 9.6524 0.0108
</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 d14628244..b183234e4 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)
- 770.3976 770.5754 775.3952 765.2222 4.1550
+ 752.9615 755.9157 756.2220 746.7469 4.3962
</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 21.478 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.575 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 685c71adb..a5e6c302f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,77 +600,31 @@ 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} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 2) {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_4: Buffer(compute_3, float32, [512], [])[cse_var_1] = 0f32
- compute_4[(cse_var_1 + 1)] = 0f32
- compute_4[(cse_var_1 + 2)] = 0f32
- compute_4[(cse_var_1 + 3)] = 0f32
- compute_4[(cse_var_1 + 4)] = 0f32
- compute_4[(cse_var_1 + 5)] = 0f32
- compute_4[(cse_var_1 + 6)] = 0f32
- compute_4[(cse_var_1 + 7)] = 0f32
- compute_4[(cse_var_1 + 8)] = 0f32
- compute_4[(cse_var_1 + 9)] = 0f32
- compute_4[(cse_var_1 + 10)] = 0f32
- compute_4[(cse_var_1 + 11)] = 0f32
- compute_4[(cse_var_1 + 12)] = 0f32
- compute_4[(cse_var_1 + 13)] = 0f32
- compute_4[(cse_var_1 + 14)] = 0f32
- compute_4[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_4: Buffer(compute_3, float32, [1024], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (cse_var_19 + 1)
- let cse_var_17: int32 = (cse_var_19 + 11)
- let cse_var_16: int32 = (cse_var_19 + 12)
- let cse_var_15: int32 = (cse_var_19 + 13)
- let cse_var_14: int32 = (cse_var_19 + 14)
- let cse_var_13: int32 = (cse_var_19 + 15)
- let cse_var_12: int32 = (cse_var_19 + 2)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 4)
- let cse_var_9: int32 = (cse_var_19 + 5)
- let cse_var_8: int32 = (cse_var_19 + 6)
- let cse_var_7: int32 = (cse_var_19 + 7)
- let cse_var_6: int32 = (cse_var_19 + 8)
- let cse_var_5: int32 = (cse_var_19 + 9)
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.outer.inner*2048)) + (i.inner*256))
- let cse_var_3: int32 = (cse_var_19 + 10)
- {
- compute_4[cse_var_19] = (compute_4[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_4[cse_var_2] = (compute_4[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
- for (i0.inner: int32, 0, 16) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_4[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -709,7 +663,7 @@ 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: 1.861 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.448 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 a162f6995..c4e6ba0dd 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>00:44.717</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.700</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.809</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>00:00.239</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>00:00.224</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>00:00.223</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>00:00.223</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>00:43.833</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>00:00.227</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>00:00.214</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>00:00.213</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>00:00.213</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>
</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 2811a7e05..ff7ca6713 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: 112.01/112.01 result: MeasureResult(costs=(0.002066808103896104,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8671989440917969, timestamp=1649120242.686281) [('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: 0.00/112.01 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.71/110.71 result: MeasureResult(costs=(0.0020911085,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.795097827911377, timestamp=1649127094.2491603) [('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: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.71 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: 0.00/112.01 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.71 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: 0.00/112.01 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.71 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: 0x00007f2ba71a6fa2
+ 12: 0x00007fade0229fa2
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: 144.62/144.62 result: MeasureResult(costs=(0.0016008005873015872,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1976046562194824, timestamp=1649120268.9132798) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 143.96/143.96 result: MeasureResult(costs=(0.00160810517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4078905582427979, timestamp=1649127120.6481802) [('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: 0.001980
+Time cost of this operator: 0.001984
</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 98b73e141..dd653a102 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 311.5 98.699 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.184 1.009 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.922 0.292 (1, 1, 10, 10, 3) 1 1
-Total_time - 315.606 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 308.9 98.719 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.993 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.288 (1, 1, 10, 10, 3) 1 1
+Total_time - 312.907 - - - -
</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 137.8 98.091 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.76 1.253 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.922 0.656 (1, 1, 10, 10, 3) 1 1
-Total_time - 140.482 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.55 96.822 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.738 2.089 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.906 1.089 (1, 1, 10, 10, 3) 1 1
+Total_time - 83.194 - - - -
</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 bbdfb3567..07d1bdc04 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>00:46.089</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:43.898</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:41.816</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>00:03.647</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>00:00.210</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>00:00.209</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>00:00.207</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>00:39.807</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>00:03.467</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>00:00.235</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>00:00.197</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>00:00.192</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>
</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 de7a70328..e94ea7d76 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>00:09.264</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.624</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:07.458</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>00:01.584</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>00:00.221</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>00:07.350</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>00:02.060</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>
</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 7a0b44532..11613309d 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>00:05.833</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.619</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.125</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>00:01.201</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>00:00.739</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
-<li><p><strong>00:00.727</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.321</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>00:00.247</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>00:00.244</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>00:00.229</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>00:02.057</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>00:01.152</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>00:00.719</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>00:00.702</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>00:00.237</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>00:00.234</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>00:00.213</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 27dd1c146..5bc933a57 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -548,8 +548,8 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
B: Buffer(B_2: Pointer(float32), float32, [32768], []),
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp3mcglfu5/input0.cc'
-source_filename = "/tmp/tmp3mcglfu5/input0.cc"
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpz3j7poeg/input0.cc'
+source_filename = "/tmp/tmpz3j7poeg/input0.cc"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index a42bf33c9..09c516674 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>
... 2730 lines suppressed ...