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 2022/04/13 11:54:44 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@61a9269d85c2966d122e1216c5c91e2d9764dc84)
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 1089b9a07 deploying docs (apache/tvm@61a9269d85c2966d122e1216c5c91e2d9764dc84)
1089b9a07 is described below
commit 1089b9a079d425e8ddd5049e51660840df5df04f
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Wed Apr 13 11:54:38 2022 +0000
deploying docs (apache/tvm@61a9269d85c2966d122e1216c5c91e2d9764dc84)
---
.../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 | 3078 +++++++++-----------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 84 +-
.../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 | 16 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 45 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
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 | 55 +-
docs/how_to/deploy_models/deploy_prequantized.html | 6 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 40 +-
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 | 3078 +++++++++-----------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 84 +-
.../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 | 16 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_relay_x86.html | 170 +-
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, 3496 insertions(+), 4316 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 5eedb9190..b6c4de516 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.zip6534bf34-ee1e-469e-a454-e33361b4eda1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip99003023-e301-4e81-b5ff-bf485559dc27 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 1cc4876dc..d78a07dce 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.631 seconds)
+ **Total running time of the script:** ( 1 minutes 6.457 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 104b00b44..349f4e742 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]
13%|#2 | 5.59M/44.7M [00:00<00:00, 57.5MB/s]
25%|##4 | 11.1M/44.7M [00:00<00:00, 57.7MB/s]
76%|#######5 | 33.9M/44.7M [00:00<00:00, 140MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
38%|###7 | 16.9M/44.7M [00:00<00:00, 177MB/s]
91%|######### | 40.6M/44.7M [00:00<00:00, 219MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 216MB/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 d5d5c237e..7fa2b3386 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 0.609 seconds)
+ **Total running time of the script:** ( 1 minutes 3.819 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 4bbc71bd0..ad2d0191f 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
=================
-**04:46.655** total execution time for **how_to_compile_models** files:
+**04:50.744** total execution time for **how_to_compile_models** files:
-- **01:05.631**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:00.609**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:56.942**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:25.305**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:21.478**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.330**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.246**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:13.398**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.716**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:06.457**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:03.819**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:58.327**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:24.959**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.637**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:21.582**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:19.156**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:12.286**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.521**: :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 ba87a5453..39fd262c4 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)
- 16.3616 16.3657 16.4626 16.2552 0.0642
+ 16.4317 16.3681 17.2338 15.9399 0.3837
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 54228619d..95727e3b4 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 | 5.70M/170M [00:00<00:02, 59.7MB/s]
7%|6 | 11.4M/170M [00:00<00:03, 49.0MB/s]
10%|# | 17.3M/170M [00:00<00:02, 54.1MB/s]
13%|#3 | 22.5M/170M [00:00<00:03, 47.4MB/s]
17%|#7 | 29.2M/170M [00:00<00:02, 54.4MB/s]
21%|## | 35.0M/170M [00:00<00:02, 56.3MB/s]
25%|##4 | 42.0M/170M [00:00<00:02, 61.5MB/s]
28%|##8 | 48.1M/170M [00:00<00:02, 62.3MB/s]
33%|###2 | 55.6M/170M [00:00<00:01, 67.0MB/s]
37%|###6 | 62.4M/170M [00:01<00:01, 68.2MB/s]
41%|#### | 68.9M/170M [00:01<00:01, 67.3MB/s]
44%|####4 | 75.4M/170M [00:01<00:01, 62.1MB/s]
48%|####8 | 82.3M/170M [00:01<00:01, 65.0MB/s]
52%|#####2 | 89.0M/170M [00:01<00:01, 66.4MB/s]
57%|#####6 | 96.1M/170M [00:01<00:01, 68.7MB/s]
61%|###### | 103M/170M [00:01<00:01, 69.3MB/s]
64%|######4 | 109M/170M [00:01<00:01, 60.8MB/s
]
68%|######7 | 115M/170M [00:01<00:00, 59.2MB/s]
71%|#######1 | 121M/170M [00:02<00:00, 56.4MB/s]
75%|#######4 | 127M/170M [00:02<00:00, 57.2MB/s]
78%|#######8 | 133M/170M [00:02<00:00, 57.6MB/s]
82%|########1 | 139M/170M [00:02<00:00, 59.4MB/s]
86%|########5 | 146M/170M [00:02<00:00, 64.1MB/s]
90%|######### | 154M/170M [00:02<00:00, 68.6MB/s]
95%|#########4| 161M/170M [00:02<00:00, 70.9MB/s]
99%|#########8| 168M/170M [00:02<00:00, 71.6MB/s]
100%|##########| 170M/170M [00:02<00:00, 63.0MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 4.12M/170M [00:00<00:04, 43.2MB/s]
5%|4 | 8.24M/170M [00:00<00:10, 16.5MB/s]
7%|6 | 11.8M/170M [00:00<00:07, 21.4MB/s]
11%|#1 | 19.0M/170M [00:00<00:04, 35.4MB/s]
15%|#4 | 25.4M/170M [00:00<00:03, 43.8MB/s]
18%|#8 | 31.2M/170M [00:00<00:02, 48.5MB/s]
23%|##2 | 38.2M/170M [00:00<00:02, 55.5MB/s]
27%|##6 | 45.6M/170M [00:01<00:02, 61.6MB/s]
31%|### | 52.5M/170M [00:01<00:01, 64.8MB/s]
35%|###4 | 59.0M/170M [00:01<00:01, 64.4MB/s]
39%|###9 | 66.5M/170M [00:01<00:01, 68.4MB/s]
43%|####3 | 73.5M/170M [00:01<00:01, 69.8MB/s]
47%|####7 | 80.5M/170M [00:01<00:01, 71.0MB/s]
51%|#####1 | 87.4M/170M [00:01<00:01, 64.3MB/s]
56%|#####5 | 94.9M/170M [00:01<00:01, 68.0MB/s]
60%|###### | 102M/170M [00:01<00:01, 70.0MB/s]
64%|######4 | 109M/170M [00:02<00:00, 70.7MB/s
]
68%|######8 | 116M/170M [00:02<00:00, 71.5MB/s]
72%|#######2 | 123M/170M [00:02<00:00, 70.3MB/s]
77%|#######6 | 130M/170M [00:02<00:00, 71.5MB/s]
81%|######## | 137M/170M [00:02<00:00, 71.9MB/s]
85%|########4 | 144M/170M [00:02<00:00, 60.9MB/s]
89%|########8 | 151M/170M [00:02<00:00, 65.0MB/s]
93%|#########3| 158M/170M [00:02<00:00, 67.9MB/s]
97%|#########7| 165M/170M [00:02<00:00, 68.0MB/s]
100%|##########| 170M/170M [00:02<00:00, 60.0MB/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 7.949 seconds)
+ **Total running time of the script:** ( 3 minutes 7.638 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 3164bb454..4fc0771ce 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, 179MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 202MB/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)
- 90.3200 90.1833 95.4850 90.0664 0.7210
+ 90.2190 90.1628 91.2818 90.0233 0.1871
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 5.848 seconds)
+ **Total running time of the script:** ( 1 minutes 5.023 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 2ce52df72..a8ccabbb5 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)
- 119.3554 119.3239 122.0983 118.5400 0.4722
+ 119.2329 119.1556 121.7348 118.5064 0.4227
@@ -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 59.238 seconds)
+ **Total running time of the script:** ( 1 minutes 53.699 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 b6a5a1b88..e278b07b7 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 20.192 seconds)
+ **Total running time of the script:** ( 1 minutes 30.038 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 e06ceaec8..51d9da4a2 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7213/132723 [00:00<00:01, 72119.92KB/s]
12%|#1 | 15896/132723 [00:00<00:01, 80767.47KB/s]
19%|#8 | 24606/132723 [00:00<00:01, 83656.79KB/s]
25%|##4 | 32972/132723 [00:00<00:01, 61255.92KB/s]
30%|##9 | 39750/132723 [00:00<00:01, 47376.13KB/s]
34%|###4 | 45226/132723 [00:00<00:02, 42350.15KB/s]
38%|###7 | 49954/132723 [00:01<00:02, 30191.98KB/s]
44%|####4 | 58426/132723 [00:01<00:01, 40214.73KB/s]
49%|####9 | 65635/132723 [00:01<00:01, 46843.32KB/s]
55%|#####4 | 72853/132723 [00:01<00:01, 51248.53KB/s]
59%|#####9 | 78885/132723 [00:01<00:01, 50045.40KB/s]
64%|######3 | 84512/132723 [00:01<00:01, 41590.83KB/s]
70%|######9 | 92479/132723 [00:01<00:00, 49952.99KB/s]
74%|#######4 | 98288/132723 [00:02<00:00, 45920.08KB/s]
79%|#######8 | 104783/132723 [00:02<00:00, 46455.93KB/s]
83%|########2
| 109817/132723 [00:02<00:00, 36298.15KB/s]
86%|########6 | 114680/132723 [00:02<00:00, 34418.68KB/s]
89%|########9 | 118501/132723 [00:02<00:00, 30380.91KB/s]
96%|#########5| 127109/132723 [00:02<00:00, 41635.57KB/s]
100%|##########| 132723/132723 [00:02<00:00, 45259.82KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6511/132723 [00:00<00:01, 65103.54KB/s]
11%|#1 | 15101/132723 [00:00<00:01, 77321.66KB/s]
18%|#7 | 23724/132723 [00:00<00:01, 81385.47KB/s]
24%|##4 | 32387/132723 [00:00<00:01, 83450.90KB/s]
31%|### | 41072/132723 [00:00<00:01, 84674.51KB/s]
37%|###7 | 49705/132723 [00:00<00:00, 85233.70KB/s]
44%|####3 | 58360/132723 [00:00<00:00, 85662.28KB/s]
50%|##### | 66927/132723 [00:00<00:00, 66846.49KB/s]
56%|#####5 | 74214/132723 [00:01<00:00, 64445.54KB/s]
62%|######1 | 81905/132723 [00:01<00:00, 55337.80KB/s]
67%|######7 | 89294/132723 [00:01<00:00, 59663.72KB/s]
74%|#######3 | 97873/132723 [00:01<00:00, 66193.09KB/s]
79%|#######9 | 104961/132723 [00:01<00:00, 67075.65KB/s]
84%|########4 | 112007/132723 [00:01<00:00, 64879.24KB/s]
89%|########9 | 118734/132723 [00:01<00:00, 52072.39KB/s]
94%|########
#3| 124471/132723 [00:01<00:00, 46732.75KB/s]
99%|#########9| 131879/132723 [00:02<00:00, 52949.32KB/s]
100%|##########| 132723/132723 [00:02<00:00, 63662.80KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 26.549 seconds)
+ **Total running time of the script:** ( 2 minutes 26.378 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 efdacaa2d..a7493c4f0 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
=================
-**10:50.476** total execution time for **how_to_deploy_models** files:
+**10:52.883** total execution time for **how_to_deploy_models** files:
-- **03:07.949**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:26.549**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:59.238**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:20.192**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:05.848**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.307**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.198**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.193**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:07.638**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:26.378**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:53.699**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:30.038**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:05.023**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:28.331**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.581**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.195**: :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 f9dbbf808..8fa8033de 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.zipa76a2999-c729-4b95-82e0-63d052e0fcf6 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip6dea1663-573f-407d-905d-909c302ff125 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 60ac9460b..e86ff7bff 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:38.856** total execution time for **how_to_extend_tvm** files:
+**00:38.444** total execution time for **how_to_extend_tvm** files:
-- **00:35.282**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.287**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.083**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.203**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.941**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.248**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.059**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.196**: :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 43ba5eb3d..a1218e75d 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: 6204us [6204us] (45.52%; 45.52%)
- FoldScaleAxis: 7426us [2us] (54.48%; 54.48%)
- FoldConstant: 7424us [1528us] (54.47%; 99.97%)
- InferType: 5896us [5896us] (43.26%; 79.42%)
+ InferType: 6025us [6025us] (45.56%; 45.56%)
+ FoldScaleAxis: 7200us [2us] (54.44%; 54.44%)
+ FoldConstant: 7197us [1472us] (54.43%; 99.97%)
+ InferType: 5725us [5725us] (43.29%; 79.54%)
@@ -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: 5933us [5933us] (44.71%; 44.71%)
- FoldScaleAxis: 7336us [2us] (55.29%; 55.29%)
- FoldConstant: 7334us [1534us] (55.27%; 99.97%)
- InferType: 5801us [5801us] (43.72%; 79.09%)
+ InferType: 5760us [5760us] (44.59%; 44.59%)
+ FoldScaleAxis: 7159us [2us] (55.41%; 55.41%)
+ FoldConstant: 7157us [1481us] (55.40%; 99.98%)
+ InferType: 5676us [5676us] (43.94%; 79.30%)
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 ebc54179e..376edd97d 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: 44.106231 ms
+ Convolution: 33.438292 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 bcfeefec1..f1a1a0ff7 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: 10.275856 ms
+ conv2d with tensor core: 8.287361 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 3fbb35489..c7dc3fa22 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: 0.019343
- Baseline: 3.459110
+ Numpy running time: 0.019586
+ Baseline: 3.218875
@@ -209,7 +209,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.313375
+ Opt1: 0.302819
@@ -307,7 +307,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345109
+ Opt2: 0.338196
@@ -398,7 +398,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.120693
+ Opt3: 0.118329
@@ -516,7 +516,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111670
+ Opt4: 0.110258
@@ -633,7 +633,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111665
+ Opt5: 0.111787
@@ -753,7 +753,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145984
+ Opt6: 0.144597
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 839480be2..953c63cc7 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
=================
-**00:35.683** total execution time for **how_to_optimize_operators** files:
+**00:34.679** total execution time for **how_to_optimize_operators** files:
-- **00:33.007**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.460**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.217**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.002**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.445**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.232**: :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 eadfae1f5..4316e794d 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**04:59.151** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:21.773**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.708**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.080**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:16.968**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.993**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.629**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:58.774** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:24.044**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:20.225**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.934**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:16.020**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.948**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.604**: :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 4f0835778..3332e4d2c 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
@@ -221,943 +221,669 @@ 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" = 112;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [112]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [512]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 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, 32) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (ry.outer.outer*7)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [112], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1: Buffer(kernel.shared, float32, [512], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4608)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9216)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13824)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18432)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23040)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27648)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41472)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46080)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50688)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55296)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59904)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69120)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78336)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82944)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87552)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92160)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101376)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105984)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115200)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119808)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124416)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133632)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138240)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142848)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4609)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9217)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13825)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18433)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23041)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27649)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32257)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36865)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41473)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46081)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50689)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55297)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59905)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64513)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69121)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73729)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78337)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82945)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87553)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92161)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96769)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101377)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105985)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110593)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115201)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119809)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124417)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129025)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133633)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138241)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142849)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 2), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 4), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 6), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 1), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 3), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 5), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4610)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9218)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13826)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18434)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23042)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27650)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32258)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36866)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41474)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46082)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50690)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55298)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59906)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64514)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69122)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73730)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78338)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82946)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87554)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92162)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96770)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101378)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105986)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110594)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115202)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119810)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124418)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129026)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133634)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138242)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142850)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((blockIdx.x*147456) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*147456) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 44), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 36), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 148), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 68), 72))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(floordiv(threadIdx.x, 49)*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1728)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 648)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1224)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1800)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 577)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1153)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1729)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 649)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1225)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1801)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1730)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 650)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1226)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1802)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1737)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 657)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1233)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1809)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 586)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1162)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1738)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 658)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1234)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1810)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1739)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 659)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1235)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1811)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 579)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1155)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1731)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 651)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1227)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1803)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 580)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1156)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1732)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 652)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1228)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1804)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1733)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 653)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1229)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1805)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 588)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1164)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1740)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 660)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1236)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1812)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 589)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1165)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1741)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 661)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1237)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1813)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1742)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 662)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1238)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1814)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 582)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1158)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1734)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 654)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1230)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1806)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 583)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1159)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1735)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 655)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1231)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1807)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1736)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 656)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1232)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1808)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 591)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1167)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1743)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 663)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1239)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1815)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 592)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1168)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1744)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 664)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1240)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1816)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1745)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 665)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1241)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1817)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 594)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1170)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1746)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 666)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1242)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1818)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 595)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1171)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1747)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 667)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1243)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1819)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1748)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 668)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1244)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1820)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 603)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1179)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1755)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 675)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1251)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1827)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 604)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1180)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1756)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 676)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1252)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1828)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1757)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 677)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1253)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1829)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 597)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1173)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1749)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 669)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1245)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1821)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 598)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1174)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1750)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 670)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1246)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1822)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1751)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 671)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1247)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1823)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 606)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1182)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1758)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 678)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1254)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1830)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 607)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1183)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1759)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 679)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1255)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1831)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1760)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 680)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1256)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1832)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 600)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1176)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1752)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 672)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1248)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1824)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 601)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1177)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1753)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 673)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1249)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1825)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1754)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 674)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1250)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1826)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 609)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1185)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1761)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 681)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1257)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1833)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 610)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1186)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1762)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 682)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1258)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1834)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1763)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 683)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1259)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1835)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 612)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1188)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1764)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 684)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1260)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1836)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 613)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1189)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1765)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 685)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1261)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1837)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 614)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1766)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 686)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1262)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1838)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 621)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1197)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1773)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 693)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1269)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1845)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 622)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1198)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1774)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 694)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1270)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1846)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1775)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 695)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1271)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1847)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 615)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1191)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1767)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 687)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1263)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1839)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 616)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 688)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1264)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1840)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 617)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1769)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 689)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1265)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1841)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 624)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1200)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1776)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 696)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1272)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1848)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 625)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1201)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1777)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 697)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1273)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1849)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 626)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1778)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 698)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1274)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1850)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 618)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1770)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 690)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1266)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1842)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 619)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1771)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 691)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1267)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1843)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 620)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1772)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 692)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1268)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1844)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 627)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1203)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1779)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 699)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1275)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1851)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 628)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1204)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1780)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 700)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1276)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1852)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 629)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1781)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 701)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1277)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1853)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 630)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1206)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1782)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 702)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1278)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1854)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 631)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1207)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1783)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 703)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1279)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1855)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 632)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1784)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 704)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1280)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1856)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 639)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1215)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1791)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 711)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1287)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1863)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 640)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1216)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1792)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 712)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1288)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1864)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 641)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1217)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1793)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 713)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1289)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1865)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 633)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1209)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1785)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 705)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1281)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1857)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 634)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1210)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1786)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 706)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1282)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1858)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 635)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1787)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 707)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1283)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1859)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 642)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1218)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1794)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 714)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1290)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1866)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 643)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1219)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1795)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 715)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1291)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1867)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 644)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1220)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1796)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 716)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1292)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1868)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 636)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1212)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1788)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 708)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1284)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1860)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 637)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1213)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1789)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 709)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1285)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1861)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 638)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1790)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 710)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1286)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1862)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 645)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1221)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1797)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 717)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1293)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1869)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 646)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1222)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1798)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 718)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1294)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1870)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 647)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1223)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1799)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 719)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1295)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1871)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*32) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
}
}
}
@@ -1210,7 +936,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.407 ms
+ Execution time of this operator: 0.273 ms
@@ -1256,34 +982,34 @@ 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=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+ conv2d_nchw_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=4)
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=7)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=2)
- 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_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=4)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1303,12 +1029,12 @@ 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=16)
+ 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=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
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=16)
+ 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=196)
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)
@@ -1328,827 +1054,653 @@ 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__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[112];
- __shared__ float kernel_shared[512];
+ extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[2304];
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 < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4608)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9216)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13824)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18432)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23040)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27648)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41472)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46080)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50688)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55296)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59904)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69120)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78336)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82944)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87552)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92160)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101376)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105984)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115200)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119808)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124416)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133632)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138240)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142848)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 7)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4609)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9217)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13825)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18433)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23041)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27649)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32257)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36865)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41473)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46081)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50689)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55297)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59905)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64513)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69121)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73729)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78337)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82945)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87553)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92161)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96769)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101377)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105985)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110593)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115201)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119809)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124417)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129025)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133633)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138241)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142849)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 2) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 4) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 6) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 1) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 3) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 5) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 6)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4610)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9218)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13826)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18434)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23042)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27650)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32258)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36866)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41474)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46082)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50690)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55298)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59906)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64514)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69122)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73730)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78338)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82946)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87554)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92162)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96770)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101378)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105986)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110594)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115202)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119810)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124418)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129026)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133634)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138242)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142850)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
}
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 52) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 12) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 44) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 4) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 36) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ if (((int)threadIdx.x) < 148) {
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 68) % 72))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1728)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 648)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1224)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1800)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1153)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1729)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 649)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1225)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1801)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1730)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 650)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1226)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1802)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1737)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 657)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1233)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1809)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1162)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1738)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 658)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1234)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1810)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1739)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 659)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1235)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1811)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1155)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1731)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 651)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1227)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1803)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1156)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1732)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 652)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1228)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1804)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1733)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 653)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1229)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1805)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 588)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1164)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1740)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 660)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1236)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1812)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 589)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1165)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1741)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 661)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1237)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1813)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1742)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 662)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1238)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1814)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1158)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1734)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 654)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1230)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1806)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1159)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1735)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 655)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1231)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1807)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1736)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 656)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1232)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1808)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 591)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1167)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1743)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 663)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1239)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1815)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 592)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1168)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1744)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 664)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1240)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1816)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1745)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 665)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1241)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1817)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 594)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1170)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1746)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 666)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1242)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1818)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 595)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1171)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1747)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 667)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1243)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1819)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1748)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 668)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1244)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1820)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 603)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1179)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1755)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 675)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1251)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1827)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 604)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1180)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1756)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 676)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1252)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1828)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1757)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 677)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1253)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1829)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 597)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1173)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1749)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 669)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1245)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1821)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 598)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1174)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1750)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 670)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1246)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1822)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1751)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 671)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1247)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1823)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 606)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1182)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1758)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 678)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1254)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1830)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 607)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1183)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1759)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 679)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1255)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1831)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1760)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 680)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1256)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1832)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 600)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1176)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1752)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 672)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1248)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1824)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 601)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1177)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1753)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 673)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1249)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1825)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1754)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 674)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1250)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1826)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 609)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1185)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1761)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 681)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1257)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1833)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 610)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1186)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1762)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 682)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1258)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1834)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1763)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 683)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1259)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1835)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 612)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1188)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1764)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 684)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1260)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1836)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 613)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1189)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1765)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 685)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1261)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1837)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 614)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1766)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 686)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1262)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1838)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 621)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1197)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1773)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 693)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1269)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1845)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 622)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1198)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1774)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 694)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1270)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1846)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1775)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 695)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1271)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1847)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 615)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1191)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1767)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 687)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1263)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1839)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 616)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 688)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1264)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1840)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 617)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1769)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 689)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1265)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1841)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 624)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1200)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1776)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 696)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1272)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1848)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 625)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1201)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1777)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 697)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1273)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1849)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 626)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1778)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 698)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1274)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1850)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 618)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1770)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 690)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1266)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1842)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 619)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1771)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 691)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1267)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1843)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 620)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1772)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 692)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1268)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1844)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 627)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1203)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1779)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 699)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1275)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1851)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 628)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1204)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1780)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 700)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1276)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1852)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 629)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1781)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 701)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1277)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1853)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 630)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1206)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1782)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 702)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1278)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1854)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 631)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1207)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1783)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 703)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1279)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1855)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 632)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1784)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 704)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1280)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1856)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 639)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1215)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1791)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 711)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1287)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1863)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 640)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1216)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1792)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 712)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1288)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1864)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 641)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1217)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1793)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 713)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1289)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1865)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 633)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1209)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1785)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 705)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1281)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1857)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 634)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1210)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1786)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 706)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1282)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1858)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 635)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1787)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 707)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1283)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1859)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 642)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1218)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1794)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 714)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1290)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1866)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 643)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1219)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1795)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 715)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1291)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1867)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 644)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1220)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1796)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 716)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1292)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1868)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 636)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1212)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1788)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 708)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1284)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1860)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 637)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1213)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1789)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 709)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1285)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1861)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 638)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1790)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 710)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1286)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1862)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 645)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1221)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1797)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 717)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1293)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1869)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 646)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1222)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1798)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 718)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1294)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1870)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 647)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1223)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1799)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 719)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1295)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1871)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
}
}
@@ -2207,7 +1759,7 @@ 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 21.773 seconds)
+ **Total running time of the script:** ( 2 minutes 24.044 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 7c04fdbfc..8351fa63f 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)
- 9.8660 9.8896 9.8902 9.8183 0.0337
+ 9.5010 9.4928 9.5401 9.4703 0.0291
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 9234d269a..c5f8a53db 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)
- 778.8489 777.8527 784.6227 774.0715 4.3648
+ 767.7877 771.1795 772.1621 760.0214 5.5062
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.708 seconds)
+ **Total running time of the script:** ( 1 minutes 20.225 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 1d58b89d6..2092fb212 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
@@ -362,30 +362,76 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [4096], [])[((((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [1024], [])[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 (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*256) + (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[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 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, 32) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_18: int32 = (cse_var_20 + 1)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_20 + 10)
+ {
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
+ for (i0.inner: int32, 0, 32) {
for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ let cse_var_22: 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_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
}
}
}
@@ -440,7 +486,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.551 ms
+ Execution time of this operator: 1.815 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 93934d815..63b949b4e 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
=================
-**00:44.476** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.906** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.606**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.214**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.214**: :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_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:43.050**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.211**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.211**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.211**: :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 178f1306e..ef1e6edcf 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.26/42.26 result: MeasureResult(costs=(0.005477762736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6445176601409912, timestamp=1649839267.0031972) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.34/42.34 result: MeasureResult(costs=(0.005467562947368421,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6258668899536133, timestamp=1649846712.621077) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.34 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: 0x00007f33e2367fa2
+ 12: 0x00007f0ffb099fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 143.86/143.86 result: MeasureResult(costs=(0.0016092658000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4409630298614502, timestamp=1649839293.3875308) [('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: 145.05/145.05 result: MeasureResult(costs=(0.001596039126984127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1495342254638672, timestamp=1649846738.0719416) [('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: 0.002036
+ Time cost of this operator: 0.002043
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 986636dfe..7d024a0bb 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 313.0 98.72 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.989 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.291 (1, 1, 10, 10, 3) 1 1
- Total_time - 317.057 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.3 98.719 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.131 0.987 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.367 - - - -
@@ -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 82.25 96.867 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.049 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 1.084 (1, 1, 10, 10, 3) 1 1
- Total_time - 84.91 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.8 97.106 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.736 1.877 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.94 1.017 (1, 1, 10, 10, 3) 1 1
+ Total_time - 92.476 - - - -
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 186bd98d2..df73d89a6 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:44.664** total execution time for **how_to_work_with_microtvm** files:
+**00:44.708** total execution time for **how_to_work_with_microtvm** files:
-- **00:40.576**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.492**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.202**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.198**: :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``)
+- **00:40.629**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.502**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.194**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.193**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.191**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.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 90031ab17..53fbb96fa 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
=================
-**00:08.066** total execution time for **how_to_work_with_relay** files:
+**00:09.098** total execution time for **how_to_work_with_relay** files:
-- **00:06.127**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.727**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.212**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:07.192**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.692**: :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 a6e2c00cf..62d00c5f8 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
=================
-**00:05.543** total execution time for **how_to_work_with_schedules** files:
+**00:05.776** total execution time for **how_to_work_with_schedules** files:
-- **00:02.012**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.130**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.705**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.696**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.307**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:02.119**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.200**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.737**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.717**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.308**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
- **00:00.238**: :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``)
-- **00:00.222**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:00.236**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.221**: :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 1a1e6b308..abbe0f804 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -314,7 +314,7 @@ 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/tmp99a8lv2p/input0.cc'\nsource_filename = \"/tmp/tmp99a8lv2p/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp6euf6s_k/input0.cc'\nsource_filename = \"/tmp/tmp6euf6s_k/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = alloca float*, align 8\n %8 = alloca float*, align 8\n %9 = alloca floa [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
index 9654443b8..53b126b75 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.919** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.615** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.711**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.207**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.413**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.202**: :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 0b863eba1..fd451a4f4 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 22.07s!
+ resnet18_v1 inference graph built in 21.86s!
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 f71a8c462..b2da199dd 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 15.24s!
+ yolov3-tiny inference graph built in 15.34s!
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 6a78c6f40..10b8b9c2d 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
=================
-**01:29.319** total execution time for **topic_vta_tutorials_frontend** files:
+**01:29.503** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.176**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:42.143**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:47.468**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:42.035**: :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 2a0dc7ee4..c19f71192 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
=================
-**00:03.465** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.533** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:02.928**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.537**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.984**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.549**: :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 76a1746a4..4707f0936 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:00.967** total execution time for **topic_vta_tutorials** files:
+**00:00.992** total execution time for **topic_vta_tutorials** files:
-- **00:00.493**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.474**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.504**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.487**: :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 bcd7a8300..509bd11c0 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -185,7 +185,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E
+
@@ -305,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.526 ms
+ Execution time of this operator: 93.485 ms
@@ -414,11 +414,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.859 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 86803ea4d..2eb37c2ff 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': 495.3681292500005, 'median': 494.94245695000245, 'std': 1.383756620744177}
+ {'mean': 497.02573500000653, 'median': 497.06994624998515, 'std': 2.1784635874530456}
@@ -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: 14.09/ 14.17 GFLOPS | Progress: (4/10) | 5.57 s
[Task 1/25] Current/Best: 6.51/ 23.91 GFLOPS | Progress: (8/10) | 7.86 s
[Task 1/25] Current/Best: 16.01/ 23.91 GFLOPS | Progress: (10/10) | 8.90 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 14.78/ 14.86 GFLOPS | Progress: (4/10) | 2.09 s
[Task 2/25] Current/Best: 15.86/ 16.69 GFLOPS | Progress: (8/10) | 3.46 s
[Task 2/25] Current/Best: 6.01/ 18.93 GFLOPS | Progress: (10/10) | 3.99 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 16.90/ 16.90 GFLOPS | Progress: (4/10) | 3.66 s
[Task 3/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (8/10) | 6.00 s
[Task 3/25] Current/Best: 1.63/ 18.90 GFLOPS | Progress: (10/10) | 8.24 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 16.08/ 16.08 GFLOPS | Progress: (4/10) | 7.93 s
[Task 4/25] Current/Best: 17.05/ 17.07 GFLOPS | Progress: (8/10) | 12.10 s
[Task 4/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (10/10) | 13.14 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 13.44/ 13.44 GFLOPS | Progress: (4/10) | 3.51 s
[Task 5/25] Current/Best: 3.43/ 13.44 GFLOPS | Progress: (8/10) | 5.44 s
[Task 5/25] Current/Best: 6.46/ 13.44 GFLOPS | Progress: (10/10) | 6.79 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 16.19/ 16.19 GFLOPS | Progress: (4/10) | 3.89 s
[Task 6/25] Current/Best: 15.39/ 16.19 GFLOPS | Progress: (8/10) | 8.74 s
[Task 6/25] Current/Best: 12.69/ 16.19 GFLOPS | Progress: (10/10) | 11.64 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 8.76/ 16.12 GFLOPS | Progress: (4/10) | 3.98 s
[Task 7/25] Current/Best: 15.05/ 17.32 GFLOPS | Progress: (8/10) | 5.72 s
[Task 7/25] Current/Best: 16.90/ 17.32 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: 14.19/ 14.70 GFLOPS | Progress: (4/10) | 8.96 s
[Task 8/25] Current/Best: 11.85/ 14.70 GFLOPS | Progress: (8/10) | 13.00 s
[Task 8/25] Current/Best: 18.54/ 18.54 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: 15.64/ 22.58 GFLOPS | Progress: (4/10) | 7.04 s
[Task 9/25] Current/Best: 10.24/ 22.58 GFLOPS | Progress: (8/10) | 28.10 s
[Task 9/25] Current/Best: 7.65/ 22.58 GFLOPS | Progress: (10/10) | 30.45 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 18.59/ 18.59 GFLOPS | Progress: (4/10) | 2.91 s
[Task 10/25] Current/Best: 14.21/ 18.59 GFLOPS | Progress: (8/10) | 4.61 s
[Task 10/25] Current/Best: 2.68/ 18.59 GFLOPS | Progress: (10/10) | 6.09 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 18.26/ 18.26 GFLOPS | Progress: (4/10) | 3.11 s
[Task 11/25] Current/Best: 24.06/ 24.06 GFLOPS | Progress: (8/10) | 5.99 s
[Task 11/25] Current/Best: 18.90/ 24.06 GFLOPS | Progress: (10/10) | 6.71 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 8.41/ 15.21 GFLOPS | Progress: (4/10) | 5.85 s
[Task 12/25] Current/Best: 10.00/ 16.29 GFLOPS | Progress: (8/10) | 10.14 s
[Task 12/25] Current/Best: 12.78/ 16.29 GFLOPS | Progress: (10/10) | 11.03 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 9.48/ 18.97 GFLOPS | Progress: (4/10) | 3.92 s
[Task 13/25] Current/Best: 7.33/ 18.97 GFLOPS | Progress: (8/10) | 7.68 s
[Task 13/25] Current/Best: 7.94/ 18.97 GFLOPS | Progress: (10/10) | 9.21 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 11.07/ 18.64 GFLOPS | Progress: (4/10) | 5.70 s
[Task 14/25] Current/Best: 7.51/ 18.97 GFLOPS | Progress: (8/10) | 9.07 s
[Task 14/25] Current/Best: 21.03/ 21.03 GFLOPS | Progress: (10/10) | 9.79 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 17.44/ 17.44 GFLOPS | Progress: (4/10) | 3.86 s
[Task 15/25] Current/Best: 7.07/ 17.44 GFLOPS | Progress: (8/10) | 5.13 s
[Task 15/25] Current/Best: 10.24/ 17.44 GFLOPS | Progress: (10/10) | 5.84 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 11.45/ 17.08 GFLOPS | Progress: (4/10) | 5.46 s
[Task 1/25] Current/Best: 11.57/ 19.54 GFLOPS | Progress: (8/10) | 7.89 s
[Task 1/25] Current/Best: 12.78/ 19.54 GFLOPS | Progress: (10/10) | 10.31 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 10.61/ 17.03 GFLOPS | Progress: (4/10) | 3.15 s
[Task 2/25] Current/Best: 21.63/ 21.63 GFLOPS | Progress: (8/10) | 4.19 s
[Task 2/25] Current/Best: 20.00/ 21.63 GFLOPS | Progress: (10/10) | 5.20 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 3.22/ 20.98 GFLOPS | Progress: (4/10) | 3.49 s
[Task 3/25] Current/Best: 14.90/ 20.98 GFLOPS | Progress: (8/10) | 6.16 s
[Task 3/25] Current/Best: 5.47/ 20.98 GFLOPS | Progress: (10/10) | 7.73 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 8.11/ 17.06 GFLOPS | Progress: (4/10) | 2.48 s
[Task 4/25] Current/Best: 22.65/ 22.65 GFLOPS | Progress: (8/10) | 6.35 s
[Task 4/25] Current/Best: 12.62/ 22.65 GFLOPS | Progress: (10/10) | 7.34 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 17.05/ 17.05 GFLOPS | Progress: (4/10) | 2.87 s
[Task 5/25] Current/Best: 17.82/ 17.82 GFLOPS | Progress: (8/10) | 4.81 s
[Task 5/25] Current/Best: 10.60/ 17.82 GFLOPS | Progress: (10/10) | 5.57 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 15.75/ 17.15 GFLOPS | Progress: (4/10) | 3.85 s
[Task 6/25] Current/Best: 3.25/ 17.15 GFLOPS | Progress: (8/10) | 7.15 s
[Task 6/25] Current/Best: 17.65/ 17.65 GFLOPS | Progress: (10/10) | 8.42 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 18.41/ 18.41 GFLOPS | Progress: (4/10) | 2.98 s
[Task 7/25] Current/Best: 18.88/ 20.85 GFLOPS | Progress: (8/10) | 4.75 s
[Task 7/25] Current/Best: 14.13/ 20.85 GFLOPS | Progress: (10/10) | 5.75 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 3.94/ 19.64 GFLOPS | Progress: (4/10) | 3.97 s
[Task 8/25] Current/Best: 16.57/ 19.64 GFLOPS | Progress: (8/10) | 8.28 s
[Task 8/25] Current/Best: 18.81/ 19.64 GFLOPS | Progress: (10/10) | 9.21 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 5.27/ 12.29 GFLOPS | Progress: (4/10) | 5.03 s
[Task 9/25] Current/Best: 13.84/ 18.08 GFLOPS | Progress: (8/10) | 6.29 s
[Task 9/25] Current/Best: 20.79/ 20.79 GFLOPS | Progress: (10/10) | 8.37 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 14.13/ 18.35 GFLOPS | Progress: (4/10) | 2.27 s
[Task 10/25] Current/Best: 11.67/ 18.35 GFLOPS | Progress: (8/10) | 3.70 s
[Task 10/25] Current/Best: 11.19/ 18.35 GFLOPS | Progress: (10/10) | 4.76 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 17.20/ 23.03 GFLOPS | Progress: (4/10) | 3.06 s
[Task 11/25] Current/Best: 12.15/ 23.03 GFLOPS | Progress: (8/10) | 6.25 s
[Task 11/25] Current/Best: 9.49/ 23.03 GFLOPS | Progress: (10/10) | 7.39 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 5.34/ 18.24 GFLOPS | Progress: (4/10) | 4.49 s
[Task 12/25] Current/Best: 18.30/ 18.30 GFLOPS | Progress: (8/10) | 6.77 s
[Task 12/25] Current/Best: 16.08/ 18.30 GFLOPS | Progress: (10/10) | 10.22 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 8.61/ 17.05 GFLOPS | Progress: (4/10) | 3.75 s
[Task 13/25] Current/Best: 16.29/ 17.05 GFLOPS | Progress: (8/10) | 7.03 s
[Task 13/25] Current/Best: 11.18/ 18.15 GFLOPS | Progress: (10/10) | 9.94 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 5.09/ 15.50 GFLOPS | Progress: (4/10) | 6.53 s
[Task 14/25] Current/Best: 13.80/ 18.31 GFLOPS | Progress: (8/10) | 10.23 s
[Task 14/25] Current/Best: 10.08/ 18.31 GFLOPS | Progress: (10/10) | 11.43 s Done.
+
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 16.02/ 16.40 GFLOPS | Progress: (4/10) | 2.44 s
[Task 15/25] Current/Best: 9.52/ 22.53 GFLOPS | Progress: (8/10) | 5.73 s
[Task 15/25] Current/Best: 7.10/ 23.81 GFLOPS | Progress: (10/10) | 6.87 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 8.76/ 21.35 GFLOPS | Progress: (4/10) | 2.44 s
[Task 16/25] Current/Best: 20.72/ 21.35 GFLOPS | Progress: (8/10) | 3.91 s
[Task 16/25] Current/Best: 6.79/ 21.35 GFLOPS | Progress: (10/10) | 5.56 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 18.34/ 18.34 GFLOPS | Progress: (4/10) | 4.28 s
[Task 17/25] Current/Best: 12.44/ 18.34 GFLOPS | Progress: (8/10) | 7.45 s
[Task 17/25] Current/Best: 18.33/ 20.82 GFLOPS | Progress: (10/10) | 8.66 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 10.88/ 22.25 GFLOPS | Progress: (4/10) | 7.96 s
[Task 18/25] Current/Best: 17.20/ 22.25 GFLOPS | Progress: (8/10) | 10.10 s
[Task 18/25] Current/Best: 19.23/ 22.25 GFLOPS | Progress: (10/10) | 10.92 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 16.87/ 18.16 GFLOPS | Progress: (4/10) | 3.26 s
[Task 19/25] Current/Best: 2.61/ 22.50 GFLOPS | Progress: (8/10) | 6.24 s
[Task 19/25] Current/Best: 15.20/ 22.50 GFLOPS | Progress: (10/10) | 7.52 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 15.66/ 18.99 GFLOPS | Progress: (4/10) | 4.42 s
[Task 20/25] Current/Best: 14.95/ 18.99 GFLOPS | Progress: (8/10) | 7.26 s
[Task 20/25] Current/Best: 11.15/ 18.99 GFLOPS | Progress: (10/10) | 9.32 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 16/25] Current/Best: 15.67/ 16.09 GFLOPS | Progress: (4/10) | 3.24 s
[Task 16/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (8/10) | 4.70 s
[Task 16/25] Current/Best: 14.91/ 21.03 GFLOPS | Progress: (10/10) | 5.32 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 1.56/ 19.83 GFLOPS | Progress: (4/10) | 4.91 s
[Task 17/25] Current/Best: 6.23/ 19.83 GFLOPS | Progress: (8/10) | 7.23 s
[Task 17/25] Current/Best: 22.36/ 22.36 GFLOPS | Progress: (10/10) | 7.93 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 14.84/ 14.84 GFLOPS | Progress: (4/10) | 6.00 s
[Task 18/25] Current/Best: 6.31/ 20.40 GFLOPS | Progress: (8/10) | 7.83 s
[Task 18/25] Current/Best: 10.23/ 20.40 GFLOPS | Progress: (10/10) | 12.07 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 13.41/ 17.46 GFLOPS | Progress: (4/10) | 4.14 s
[Task 19/25] Current/Best: 13.98/ 20.98 GFLOPS | Progress: (8/10) | 6.03 s
[Task 19/25] Current/Best: 14.18/ 20.98 GFLOPS | Progress: (10/10) | 7.00 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 17.79/ 20.12 GFLOPS | Progress: (4/10) | 2.46 s
[Task 20/25] Current/Best: 14.95/ 23.70 GFLOPS | Progress: (8/10) | 4.64 s
[Task 20/25] Current/Best: 7.98/ 23.70 GFLOPS | Progress: (10/10) | 5.78 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 15.47/ 21.17 GFLOPS | Progress: (4/10) | 3.94 s
[Task 21/25] Current/Best: 16.66/ 21.17 GFLOPS | Progress: (8/10) | 5.78 s
[Task 21/25] Current/Best: 8.84/ 21.17 GFLOPS | Progress: (10/10) | 6.95 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 9.73/ 9.73 GFLOPS | Progress: (4/10) | 3.66 s
[Task 22/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (8/10) | 5.67 s
[Task 22/25] Current/Best: 19.10/ 19.54 GFLOPS | Progress: (10/10) | 6.28
s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 19.10/ 20.23 GFLOPS | Progress: (4/10) | 3.26 s
[Task 23/25] Current/Best: 20.80/ 20.80 GFLOPS | Progress: (8/10) | 5.79 s
[Task 23/25] Current/Best: 11.74/ 20.80 GFLOPS | Progress: (10/10) | 8.33 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 10.24/ 10.24 GFLOPS | Progress: (4/10) | 3.98 s
[Task 24/25] Current/Best: 8.51/ 10.24 GFLOPS | Progress: (8/10) | 12.86 s
[Task 24/25] Current/Best: 2.85/ 10.24 GFLOPS | Progress: (10/10) | 14.68 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 21/25] Current/Best: 9.59/ 15.45 GFLOPS | Progress: (4/10) | 3.35 s
[Task 21/25] Current/Best: 16.50/ 16.50 GFLOPS | Progress: (8/10) | 4.76 s
[Task 21/25] Current/Best: 19.55/ 19.55 GFLOPS | Progress: (10/10) | 5.93 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 23.78/ 23.78 GFLOPS | Progress: (4/10) | 2.93 s
[Task 22/25] Current/Best: 12.18/ 23.78 GFLOPS | Progress: (8/10) | 4.78 s
[Task 22/25] Current/Best: 5.12/ 23.78 GFLOPS | Progress: (10/10) | 8.99 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 24.31/ 24.31 GFLOPS | Progress: (4/10) | 3.75 s
[Task 23/25] Current/Best: 17.90/ 24.31 GFLOPS | Progress: (8/10) | 5.75 s
[Task 23/25] Current/Best: 10.01/ 24.31 GFLOPS | Progress: (10/10) | 6.79 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 5.44/ 7.78 GFLOPS | Progress: (4/10) | 22.50 s
[Task 24/25] Current/Best: 3.48/ 7.78 GFLOPS | Progress: (8/10) | 44.30 s
[Task 24/25] Current/Best: 2.33/ 7.78 GFLOPS | Progress: (10/10) | 53.57 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 8.63/ 9.39 GFLOPS | Progress: (4/10) | 5.63 s
[Task 25/25] Current/Best: 5.98/ 9.39 GFLOPS | Progress: (8/10) | 34.45 s
[Task 25/25] Current/Best: 3.02/ 9.39 GFLOPS | Progress: (10/10) | 38.62 s
+
[Task 25/25] Current/Best: 1.54/ 8.73 GFLOPS | Progress: (4/10) | 13.87 s
[Task 25/25] Current/Best: 3.43/ 8.73 GFLOPS | Progress: (8/10) | 33.17 s
[Task 25/25] Current/Best: 2.57/ 8.73 GFLOPS | Progress: (10/10) | 49.35 s
The output from this tuning process will look something like this:
@@ -594,7 +594,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621103
+ class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356379
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -648,8 +648,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 441.83834590000515, 'median': 441.85241515006055, 'std': 0.8046901591361038}
- unoptimized: {'mean': 495.3681292500005, 'median': 494.94245695000245, 'std': 1.383756620744177}
+ optimized: {'mean': 420.28211214001203, 'median': 420.52464405001047, 'std': 1.4978198762672663}
+ unoptimized: {'mean': 497.02573500000653, 'median': 497.06994624998515, 'std': 2.1784635874530456}
@@ -669,7 +669,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 7 minutes 37.414 seconds)
+ **Total running time of the script:** ( 7 minutes 58.854 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 d33623e51..ab767800b 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
- 1.322e-07 secs/op
+ 1.291e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 3228143b1..5658f244e 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, 0x59446d0)), stage(b, placeholder(b, 0xfef9ad0)), 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, 0x214d95c0)), stage(b, placeholder(b, 0x4334120)), 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 f5c4bc235..4316eaf54 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
=================
-**10:29.030** total execution time for **tutorial** files:
+**10:33.856** total execution time for **tutorial** files:
-- **07:37.414**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:02.859**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **01:01.448**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:26.100**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:19.561**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:00.724**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.571**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.208**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.040**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.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``)
-- **00:00.034**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **07:58.854**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:58.517**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:49.283**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:26.300**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:19.199**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.719**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.598**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.218**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.044**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.043**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.041**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.040**: :ref:`sphx_glr_tutorial_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 019269bc4..0618ffddc 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: 0.000009
naive: 0.000006
@@ -436,10 +436,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.427230004599551e-06 1.0
- naive 5.8647e-06 0.6959226218815753
- parallel 6.037300000000001e-06 0.7164038476112393
- vector 2.46365e-05 2.923439847560051
+ numpy 8.65928999701282e-06 1.0
+ naive 5.8581e-06 0.6765104300723106
+ parallel 6.056700000000001e-06 0.6994453358288463
+ vector 2.4811e-05 2.8652464588388895
@@ -828,7 +828,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018198
+ Numpy running time: 0.019656
@@ -884,7 +884,7 @@ optimizations.
.. code-block:: none
- none: 3.449949
+ none: 3.207725
@@ -982,7 +982,7 @@ schedule.
.. code-block:: none
- blocking: 0.301376
+ blocking: 0.305084
@@ -1073,7 +1073,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.339956
+ vectorization: 0.344606
@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: 0.117945
+ loop permutation: 0.115036
@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: 0.109652
+ array packing: 0.107856
@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: 0.110300
+ block caching: 0.110510
@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: 0.144707
+ parallelization: 0.144767
@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 3.4499492865 1.0
- blocking 0.3013761584 0.08735669233728025
- vectorization 0.33995599480000005 0.09853941799384767
- loop permutation 0.1179445509 0.034187328886696663
- array packing 0.10965189859999999 0.03178362621997922
- block caching 0.1103004653 0.031971619331222306
- parallelization 0.1447067427 0.04194459995868696
+ none 3.2077253931999996 1.0
+ blocking 0.30508393930000005 0.09510911998475371
+ vectorization 0.3446056493 0.10742990968944019
+ loop permutation 0.11503582369999998 0.035862117107612265
+ array packing 0.1078560256 0.033623833832111094
+ block caching 0.1105101377 0.03445124633619464
+ parallelization 0.14476745100000002 0.04513087414118739
@@ -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 1.448 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index a6d7973c1..f92eaff07 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-5cfb4bc3d0e39ac59b9beec22852456489974969
+61a9269d85c2966d122e1216c5c91e2d9764dc84
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index d179e3f86..7ce6360a0 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.zip6534bf34-ee1e-469e-a454-e33361b4eda1 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.zip99003023-e301-4e81-b5ff-bf485559dc27 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 3f5a43e4d..025c4593e 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 5.631 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.457 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 96e347237..fd386bb38 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -386,10 +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]
- 13%|#2 | 5.59M/44.7M [00:00<00:00, 57.5MB/s]
- 25%|##4 | 11.1M/44.7M [00:00<00:00, 57.7MB/s]
- 76%|#######5 | 33.9M/44.7M [00:00<00:00, 140MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 134MB/s]
+ 38%|###7 | 16.9M/44.7M [00:00<00:00, 177MB/s]
+ 91%|######### | 40.6M/44.7M [00:00<00:00, 219MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 216MB/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 64148c6e5..a9bda1396 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 0.609 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.819 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 a4511c3fe..e94736555 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>04:46.655</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>04:50.744</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:05.631</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>01:00.609</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>00:56.942</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>00:25.305</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>00:21.478</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:21.330</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:19.246</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>00:13.398</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>00:02.716</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>01:06.457</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>01:03.819</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>00:58.327</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>00:24.959</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>00:21.637</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>00:21.582</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:19.156</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:12.286</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>00:02.521</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 670732fe4..53e12647a 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)
- 16.3616 16.3657 16.4626 16.2552 0.0642
+ 16.4317 16.3681 17.2338 15.9399 0.3837
</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 b4e52f309..b32f2d162 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,33 +409,32 @@ 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 | 5.70M/170M [00:00<00:02, 59.7MB/s]
- 7%|6 | 11.4M/170M [00:00<00:03, 49.0MB/s]
- 10%|# | 17.3M/170M [00:00<00:02, 54.1MB/s]
- 13%|#3 | 22.5M/170M [00:00<00:03, 47.4MB/s]
- 17%|#7 | 29.2M/170M [00:00<00:02, 54.4MB/s]
- 21%|## | 35.0M/170M [00:00<00:02, 56.3MB/s]
- 25%|##4 | 42.0M/170M [00:00<00:02, 61.5MB/s]
- 28%|##8 | 48.1M/170M [00:00<00:02, 62.3MB/s]
- 33%|###2 | 55.6M/170M [00:00<00:01, 67.0MB/s]
- 37%|###6 | 62.4M/170M [00:01<00:01, 68.2MB/s]
- 41%|#### | 68.9M/170M [00:01<00:01, 67.3MB/s]
- 44%|####4 | 75.4M/170M [00:01<00:01, 62.1MB/s]
- 48%|####8 | 82.3M/170M [00:01<00:01, 65.0MB/s]
- 52%|#####2 | 89.0M/170M [00:01<00:01, 66.4MB/s]
- 57%|#####6 | 96.1M/170M [00:01<00:01, 68.7MB/s]
- 61%|###### | 103M/170M [00:01<00:01, 69.3MB/s]
- 64%|######4 | 109M/170M [00:01<00:01, 60.8MB/s]
- 68%|######7 | 115M/170M [00:01<00:00, 59.2MB/s]
- 71%|#######1 | 121M/170M [00:02<00:00, 56.4MB/s]
- 75%|#######4 | 127M/170M [00:02<00:00, 57.2MB/s]
- 78%|#######8 | 133M/170M [00:02<00:00, 57.6MB/s]
- 82%|########1 | 139M/170M [00:02<00:00, 59.4MB/s]
- 86%|########5 | 146M/170M [00:02<00:00, 64.1MB/s]
- 90%|######### | 154M/170M [00:02<00:00, 68.6MB/s]
- 95%|#########4| 161M/170M [00:02<00:00, 70.9MB/s]
- 99%|#########8| 168M/170M [00:02<00:00, 71.6MB/s]
-100%|##########| 170M/170M [00:02<00:00, 63.0MB/s]
+ 2%|2 | 4.12M/170M [00:00<00:04, 43.2MB/s]
+ 5%|4 | 8.24M/170M [00:00<00:10, 16.5MB/s]
+ 7%|6 | 11.8M/170M [00:00<00:07, 21.4MB/s]
+ 11%|#1 | 19.0M/170M [00:00<00:04, 35.4MB/s]
+ 15%|#4 | 25.4M/170M [00:00<00:03, 43.8MB/s]
+ 18%|#8 | 31.2M/170M [00:00<00:02, 48.5MB/s]
+ 23%|##2 | 38.2M/170M [00:00<00:02, 55.5MB/s]
+ 27%|##6 | 45.6M/170M [00:01<00:02, 61.6MB/s]
+ 31%|### | 52.5M/170M [00:01<00:01, 64.8MB/s]
+ 35%|###4 | 59.0M/170M [00:01<00:01, 64.4MB/s]
+ 39%|###9 | 66.5M/170M [00:01<00:01, 68.4MB/s]
+ 43%|####3 | 73.5M/170M [00:01<00:01, 69.8MB/s]
+ 47%|####7 | 80.5M/170M [00:01<00:01, 71.0MB/s]
+ 51%|#####1 | 87.4M/170M [00:01<00:01, 64.3MB/s]
+ 56%|#####5 | 94.9M/170M [00:01<00:01, 68.0MB/s]
+ 60%|###### | 102M/170M [00:01<00:01, 70.0MB/s]
+ 64%|######4 | 109M/170M [00:02<00:00, 70.7MB/s]
+ 68%|######8 | 116M/170M [00:02<00:00, 71.5MB/s]
+ 72%|#######2 | 123M/170M [00:02<00:00, 70.3MB/s]
+ 77%|#######6 | 130M/170M [00:02<00:00, 71.5MB/s]
+ 81%|######## | 137M/170M [00:02<00:00, 71.9MB/s]
+ 85%|########4 | 144M/170M [00:02<00:00, 60.9MB/s]
+ 89%|########8 | 151M/170M [00:02<00:00, 65.0MB/s]
+ 93%|#########3| 158M/170M [00:02<00:00, 67.9MB/s]
+ 97%|#########7| 165M/170M [00:02<00:00, 68.0MB/s]
+100%|##########| 170M/170M [00:02<00:00, 60.0MB/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').
@@ -528,7 +527,7 @@ 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 7.949 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 7.638 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 f75d9691e..14e0ec8fc 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 179MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 202MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +539,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3200 90.1833 95.4850 90.0664 0.7210
+ 90.2190 90.1628 91.2818 90.0233 0.1871
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +578,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.848 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.023 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 499e4096e..58d085fc2 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)
- 119.3554 119.3239 122.0983 118.5400 0.4722
+ 119.2329 119.1556 121.7348 118.5064 0.4227
</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 59.238 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.699 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 f80599d7c..9d3917f67 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 20.192 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 30.038 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 15a4d5a30..4937ff553 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,26 +415,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 7213/132723 [00:00<00:01, 72119.92KB/s]
- 12%|#1 | 15896/132723 [00:00<00:01, 80767.47KB/s]
- 19%|#8 | 24606/132723 [00:00<00:01, 83656.79KB/s]
- 25%|##4 | 32972/132723 [00:00<00:01, 61255.92KB/s]
- 30%|##9 | 39750/132723 [00:00<00:01, 47376.13KB/s]
- 34%|###4 | 45226/132723 [00:00<00:02, 42350.15KB/s]
- 38%|###7 | 49954/132723 [00:01<00:02, 30191.98KB/s]
- 44%|####4 | 58426/132723 [00:01<00:01, 40214.73KB/s]
- 49%|####9 | 65635/132723 [00:01<00:01, 46843.32KB/s]
- 55%|#####4 | 72853/132723 [00:01<00:01, 51248.53KB/s]
- 59%|#####9 | 78885/132723 [00:01<00:01, 50045.40KB/s]
- 64%|######3 | 84512/132723 [00:01<00:01, 41590.83KB/s]
- 70%|######9 | 92479/132723 [00:01<00:00, 49952.99KB/s]
- 74%|#######4 | 98288/132723 [00:02<00:00, 45920.08KB/s]
- 79%|#######8 | 104783/132723 [00:02<00:00, 46455.93KB/s]
- 83%|########2 | 109817/132723 [00:02<00:00, 36298.15KB/s]
- 86%|########6 | 114680/132723 [00:02<00:00, 34418.68KB/s]
- 89%|########9 | 118501/132723 [00:02<00:00, 30380.91KB/s]
- 96%|#########5| 127109/132723 [00:02<00:00, 41635.57KB/s]
-100%|##########| 132723/132723 [00:02<00:00, 45259.82KB/s]
+ 5%|4 | 6511/132723 [00:00<00:01, 65103.54KB/s]
+ 11%|#1 | 15101/132723 [00:00<00:01, 77321.66KB/s]
+ 18%|#7 | 23724/132723 [00:00<00:01, 81385.47KB/s]
+ 24%|##4 | 32387/132723 [00:00<00:01, 83450.90KB/s]
+ 31%|### | 41072/132723 [00:00<00:01, 84674.51KB/s]
+ 37%|###7 | 49705/132723 [00:00<00:00, 85233.70KB/s]
+ 44%|####3 | 58360/132723 [00:00<00:00, 85662.28KB/s]
+ 50%|##### | 66927/132723 [00:00<00:00, 66846.49KB/s]
+ 56%|#####5 | 74214/132723 [00:01<00:00, 64445.54KB/s]
+ 62%|######1 | 81905/132723 [00:01<00:00, 55337.80KB/s]
+ 67%|######7 | 89294/132723 [00:01<00:00, 59663.72KB/s]
+ 74%|#######3 | 97873/132723 [00:01<00:00, 66193.09KB/s]
+ 79%|#######9 | 104961/132723 [00:01<00:00, 67075.65KB/s]
+ 84%|########4 | 112007/132723 [00:01<00:00, 64879.24KB/s]
+ 89%|########9 | 118734/132723 [00:01<00:00, 52072.39KB/s]
+ 94%|#########3| 124471/132723 [00:01<00:00, 46732.75KB/s]
+ 99%|#########9| 131879/132723 [00:02<00:00, 52949.32KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 63662.80KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -474,7 +472,7 @@ 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 26.549 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.378 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 61ee7b665..d60536b07 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>10:50.476</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:52.883</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:07.949</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>02:26.549</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>01:59.238</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>01:20.192</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>01:05.848</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:28.307</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>00:22.198</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>00:00.193</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>03:07.638</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>02:26.378</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>01:53.699</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>01:30.038</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>01:05.023</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:28.331</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>00:21.581</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>00:00.195</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 4dbc21fd9..a6b2614c5 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.zipa76a2999-c729-4b95-82e0-63d052e0fcf6 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.zip6dea1663-573f-407d-905d-909c302ff125 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 597bc3f23..4c5958a35 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:38.856</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:38.444</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:35.282</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>00:02.287</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>00:01.083</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.203</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:34.941</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>00:02.248</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>00:01.059</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>00:00.196</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 008eff4e7..ff743ec18 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: 6204us [6204us] (45.52%; 45.52%)
-FoldScaleAxis: 7426us [2us] (54.48%; 54.48%)
- FoldConstant: 7424us [1528us] (54.47%; 99.97%)
- InferType: 5896us [5896us] (43.26%; 79.42%)
+InferType: 6025us [6025us] (45.56%; 45.56%)
+FoldScaleAxis: 7200us [2us] (54.44%; 54.44%)
+ FoldConstant: 7197us [1472us] (54.43%; 99.97%)
+ InferType: 5725us [5725us] (43.29%; 79.54%)
</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: 5933us [5933us] (44.71%; 44.71%)
-FoldScaleAxis: 7336us [2us] (55.29%; 55.29%)
- FoldConstant: 7334us [1534us] (55.27%; 99.97%)
- InferType: 5801us [5801us] (43.72%; 79.09%)
+InferType: 5760us [5760us] (44.59%; 44.59%)
+FoldScaleAxis: 7159us [2us] (55.41%; 55.41%)
+ FoldConstant: 7157us [1481us] (55.40%; 99.98%)
+ InferType: 5676us [5676us] (43.94%; 79.30%)
</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 fe0b5c62f..6bb07be59 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: 44.106231 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.438292 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 e8ea94945..1e386c9ca 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: 10.275856 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.287361 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 2eaeebd4f..893c0ad21 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: 0.019343
-Baseline: 3.459110
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019586
+Baseline: 3.218875
</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: 0.313375
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.302819
</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: 0.345109
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338196
</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: 0.120693
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118329
</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: 0.111670
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110258
</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: 0.111665
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111787
</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: 0.145984
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144597
</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 d690c4ed8..07e74c471 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>00:35.683</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.679</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:33.007</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>00:01.460</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>00:01.217</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
+<li><p><strong>00:32.002</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.445</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.232</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 b45d9f417..79de99405 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:59.151</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:58.774</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:21.773</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>01:21.708</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>00:41.080</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>00:16.968</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>00:08.993</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>00:08.629</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>02:24.044</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>01:20.225</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>00:40.934</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>00:16.020</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>00:08.948</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>00:08.604</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 1f4422c84..aa01ca546 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
@@ -469,943 +469,669 @@ 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" = 112;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [112]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [512]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 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, 32) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (ry.outer.outer*7)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [112], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 7))), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 7))), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1: Buffer(kernel.shared, float32, [512], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4608)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9216)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13824)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18432)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23040)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27648)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32256)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36864)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41472)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46080)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50688)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55296)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59904)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69120)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73728)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78336)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82944)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87552)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92160)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96768)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101376)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105984)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110592)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115200)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119808)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124416)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129024)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133632)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138240)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142848)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 7)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 1)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4609)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9217)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13825)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18433)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23041)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27649)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32257)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36865)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41473)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46081)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50689)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55297)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59905)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64513)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69121)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73729)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78337)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82945)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87553)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92161)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96769)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101377)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105985)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110593)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115201)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119809)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124417)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129025)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133633)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138241)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142849)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[threadIdx.x_1] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod(threadIdx.x_1, 7) < 6)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod(threadIdx.x_1, 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 2), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 2), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 4), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 4), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 6), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 6), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 1), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 1), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 3), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 3), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (floormod((threadIdx.x_1 + 5), 7) < 6)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 7)*49)) + cse_var_1) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1 + 5), 7)) - 6)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 4610)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 9218)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 13826)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 18434)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 23042)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 27650)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 32258)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 36866)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 41474)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 46082)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 50690)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 55298)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 59906)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 64514)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 69122)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 73730)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 78338)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 82946)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 87554)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 92162)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 96770)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 101378)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 105986)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 110594)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 115202)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 119810)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 124418)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 129026)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 133634)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 138242)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
- kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*144)) + (threadIdx.x_2*9)) + (ry.outer.outer*3)) + 142850)]
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*32)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*32) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 1)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*32) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 2)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*32) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*32) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 4)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*32) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 5)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*32) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 6)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*32) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 7)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*32) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 8)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*32) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 9)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*32) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 10)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*32) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 11)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*32) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 12)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*32) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 13)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*32) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 14)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*32) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*32) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 15)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*32) + 31)]))
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 27)*49)) + (floordiv(floormod((threadIdx.x_1*4), 27), 3)*7)) + floormod((threadIdx [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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)], 0f [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (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, dty [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 1), [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 54), dtype=bool) {
+ 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[(((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 27)*49)) + (floormod((floordiv((threadIdx.x_1*4), 3) + 1), 9)*7)) + floormod(((threadIdx.x_1*12) + 2), [...]
+ }
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((blockIdx.x*147456) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*147456) + (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" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 44), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 36), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 148), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 68), 72))]
+ }
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(floordiv(threadIdx.x, 49)*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1728)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 648)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1224)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1800)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 577)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1153)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1729)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 649)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1225)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1801)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1154)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1730)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 650)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1226)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1802)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1737)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 657)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1233)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1809)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 586)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1162)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1738)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 658)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1234)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1810)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1163)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1739)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 659)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1235)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1811)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 579)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1155)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1731)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 651)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1227)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1803)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 580)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1156)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1732)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 652)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1228)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1804)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1157)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1733)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 653)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1229)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1805)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 588)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1164)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1740)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 660)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1236)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1812)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 589)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1165)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1741)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 661)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1237)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1813)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1166)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1742)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 662)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1238)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1814)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 582)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1158)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1734)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 654)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1230)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1806)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 583)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1159)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1735)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 655)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1231)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1807)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1160)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1736)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 656)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1232)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1808)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 591)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1167)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1743)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 663)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1239)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1815)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 592)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1168)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1744)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 664)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1240)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1816)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1169)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1745)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 665)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1241)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1817)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 594)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1170)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1746)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 666)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1242)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1818)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 595)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1171)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1747)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 667)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1243)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1819)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1172)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1748)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 668)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1244)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1820)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 603)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1179)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1755)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 675)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1251)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1827)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 604)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1180)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1756)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 676)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1252)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1828)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1181)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1757)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 677)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1253)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1829)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 597)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1173)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1749)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 669)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1245)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1821)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 598)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1174)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1750)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 670)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1246)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1822)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1175)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1751)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 671)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1247)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1823)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 606)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1182)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1758)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 678)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1254)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1830)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 607)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1183)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1759)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 679)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1255)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1831)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1184)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1760)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 680)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1256)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1832)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 600)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1176)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1752)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 672)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1248)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1824)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 601)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1177)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1753)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 673)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1249)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1825)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1178)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1754)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 674)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1250)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1826)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 609)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1185)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1761)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 681)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1257)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1833)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 610)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1186)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1762)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 682)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1258)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1834)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1187)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1763)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 683)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1259)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1835)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 612)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1188)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1764)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 684)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1260)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1836)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 613)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1189)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1765)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 685)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1261)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1837)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 614)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1190)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1766)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 686)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1262)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1838)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 621)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1197)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1773)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 693)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1269)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1845)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 622)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1198)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1774)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 694)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1270)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1846)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 623)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1199)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1775)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 695)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1271)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1847)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 615)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1191)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1767)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 687)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1263)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1839)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 616)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1192)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1768)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 688)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1264)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1840)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 617)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1193)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1769)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 689)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1265)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1841)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 624)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1200)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1776)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 696)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1272)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1848)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 625)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1201)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1777)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 697)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1273)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1849)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 626)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1202)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1778)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 698)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1274)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1850)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 618)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1194)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1770)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 690)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1266)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1842)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 619)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1195)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1771)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 691)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1267)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1843)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 620)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1196)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1772)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 692)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1268)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1844)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 627)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1203)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1779)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 699)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1275)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1851)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 628)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1204)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1780)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 700)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1276)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1852)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 629)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1205)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1781)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 701)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1277)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1853)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 630)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1206)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1782)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 702)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1278)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1854)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 631)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1207)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1783)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 703)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1279)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1855)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 632)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1208)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1784)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 704)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1280)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1856)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 639)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1215)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1791)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 711)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1287)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1863)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 640)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1216)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1792)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 712)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1288)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1864)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 641)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1217)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1793)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 713)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1289)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1865)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 633)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1209)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1785)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 705)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1281)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1857)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 634)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1210)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1786)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 706)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1282)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1858)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 635)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1211)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1787)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 707)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1283)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1859)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 642)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1218)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1794)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 714)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1290)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1866)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 643)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1219)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1795)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 715)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1291)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1867)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 644)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1220)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1796)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 716)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1292)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1868)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 636)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1212)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1788)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 708)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1284)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1860)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 637)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1213)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1789)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 709)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1285)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1861)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 638)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1214)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1790)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 710)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1286)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1862)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 645)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1221)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1797)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 717)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1293)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1869)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 646)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1222)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1798)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 718)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1294)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1870)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 647)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1223)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1799)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 719)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1295)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*144) + 1871)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i3.inner: int32, 0, 7) {
- compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*32) + (threadIdx.x*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
}
}
}
@@ -1443,7 +1169,7 @@ 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: 0.407 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.273 ms
</pre></div>
</div>
</div>
@@ -1475,34 +1201,34 @@ 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=2)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
+conv2d_nchw_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=4)
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=7)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=16)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=2)
-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_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=4)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1522,12 +1248,12 @@ 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=16)
+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=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=12)
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=16)
+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=196)
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)
@@ -1547,827 +1273,653 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
- __shared__ float pad_temp_shared[112];
- __shared__ float kernel_shared[512];
+extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
+ __shared__ float pad_temp_shared[648];
+ __shared__ float kernel_shared[2304];
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 < 32; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 7))) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 7))) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 8)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3))];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4608)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9216)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13824)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18432)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23040)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27648)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32256)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36864)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41472)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46080)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50688)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55296)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59904)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69120)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73728)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78336)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82944)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87552)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92160)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96768)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101376)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105984)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110592)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115200)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119808)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124416)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129024)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133632)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138240)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142848)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 7)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = (((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 7)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 1)];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4609)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9217)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13825)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18433)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23041)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27649)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32257)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36865)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41473)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46081)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50689)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55297)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59905)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64513)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69121)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73729)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78337)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82945)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87553)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92161)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96769)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101377)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105985)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110593)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115201)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119809)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124417)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129025)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133633)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138241)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142849)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && ((((int)threadIdx.x) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 16)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 2) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 16) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 32)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 4) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 32) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 4) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 48)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 6) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 48) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 1) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 64) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 80)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 3) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 80) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 7)) - 6)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (((((int)threadIdx.x) + 5) % 7) < 6)) ? data[((((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 96) / 7) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 7)) - 6)] : 0.000000e+00f);
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 2)];
- kernel_shared[(((int)threadIdx.x) + 16)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 4610)];
- kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 9218)];
- kernel_shared[(((int)threadIdx.x) + 48)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 13826)];
- kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 18434)];
- kernel_shared[(((int)threadIdx.x) + 80)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 23042)];
- kernel_shared[(((int)threadIdx.x) + 96)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 27650)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 32258)];
- kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 36866)];
- kernel_shared[(((int)threadIdx.x) + 144)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 41474)];
- kernel_shared[(((int)threadIdx.x) + 160)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 46082)];
- kernel_shared[(((int)threadIdx.x) + 176)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 50690)];
- kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 55298)];
- kernel_shared[(((int)threadIdx.x) + 208)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 59906)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 64514)];
- kernel_shared[(((int)threadIdx.x) + 240)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 69122)];
- kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 73730)];
- kernel_shared[(((int)threadIdx.x) + 272)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 78338)];
- kernel_shared[(((int)threadIdx.x) + 288)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 82946)];
- kernel_shared[(((int)threadIdx.x) + 304)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 87554)];
- kernel_shared[(((int)threadIdx.x) + 320)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 92162)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 96770)];
- kernel_shared[(((int)threadIdx.x) + 352)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 101378)];
- kernel_shared[(((int)threadIdx.x) + 368)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 105986)];
- kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 110594)];
- kernel_shared[(((int)threadIdx.x) + 400)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 115202)];
- kernel_shared[(((int)threadIdx.x) + 416)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 119810)];
- kernel_shared[(((int)threadIdx.x) + 432)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 124418)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 129026)];
- kernel_shared[(((int)threadIdx.x) + 464)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 133634)];
- kernel_shared[(((int)threadIdx.x) + 480)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 138242)];
- kernel_shared[(((int)threadIdx.x) + 496)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 144)) + (((int)threadIdx.x) * 9)) + (ry_outer_outer * 3)) + 142850)];
- __syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 32)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 32) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 1)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 32) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 2)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 32) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 32) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 4)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 32) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 5)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 32) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 6)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 32) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 7)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 32) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 8)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 32) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 9)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 32) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 10)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 32) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 11)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 32) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 12)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 32) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 13)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 32) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 14)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 32) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 15)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 32) + 31)]));
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
}
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ if (((int)threadIdx.x) < 54) {
+ 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);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 52) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 32) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 12) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 44) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 24) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 4) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 36) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 16) % 72))];
+ if (((int)threadIdx.x) < 148) {
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 68) % 72))];
+ }
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1728)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 648)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1224)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1800)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1153)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1729)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 649)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1225)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1801)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1154)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1730)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 650)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1226)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1802)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1737)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 657)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1233)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1809)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1162)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1738)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 658)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1234)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1810)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1163)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1739)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 659)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1235)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1811)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1155)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1731)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 651)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1227)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1803)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1156)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1732)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 652)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1228)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1804)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1157)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1733)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 653)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1229)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1805)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 588)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1164)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1740)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 660)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1236)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1812)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 589)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1165)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1741)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 661)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1237)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1813)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1166)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1742)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 662)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1238)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1814)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1158)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1734)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 654)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1230)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1806)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1159)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1735)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 655)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1231)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1807)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1160)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1736)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 656)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1232)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1808)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 591)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1167)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1743)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 663)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1239)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1815)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 592)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1168)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1744)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 664)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1240)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1816)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1169)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1745)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 665)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1241)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1817)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 594)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1170)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1746)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 666)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1242)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1818)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 595)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1171)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1747)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 667)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1243)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1819)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1172)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1748)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 668)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1244)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1820)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 603)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1179)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1755)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 675)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1251)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1827)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 604)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1180)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1756)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 676)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1252)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1828)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1181)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1757)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 677)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1253)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1829)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 597)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1173)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1749)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 669)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1245)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1821)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 598)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1174)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1750)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 670)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1246)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1822)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1175)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1751)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 671)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1247)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1823)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 606)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1182)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1758)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 678)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1254)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1830)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 607)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1183)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1759)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 679)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1255)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1831)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1184)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1760)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 680)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1256)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1832)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 600)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1176)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1752)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 672)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1248)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1824)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 601)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1177)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1753)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 673)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1249)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1825)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1178)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1754)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 674)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1250)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1826)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 609)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1185)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1761)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 681)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1257)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1833)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 610)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1186)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1762)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 682)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1258)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1834)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1187)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1763)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 683)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1259)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1835)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 612)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1188)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1764)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 684)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1260)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1836)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 613)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1189)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1765)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 685)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1261)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1837)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 614)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1190)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1766)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 686)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1262)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1838)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 621)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1197)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1773)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 693)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1269)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1845)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 622)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1198)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1774)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 694)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1270)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1846)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 623)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1199)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1775)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 695)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1271)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1847)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 615)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1191)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1767)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 687)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1263)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1839)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 616)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1192)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1768)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 688)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1264)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1840)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 617)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1193)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1769)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 689)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1265)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1841)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 624)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1200)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1776)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 696)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1272)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1848)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 625)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1201)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1777)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 697)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1273)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1849)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 626)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1202)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1778)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 698)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1274)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1850)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 618)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1194)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1770)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 690)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1266)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1842)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 619)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1195)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1771)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 691)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1267)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1843)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 620)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1196)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1772)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 692)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1268)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1844)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 627)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1203)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1779)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 699)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1275)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1851)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 628)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1204)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1780)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 700)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1276)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1852)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 629)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1205)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1781)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 701)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1277)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1853)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 630)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1206)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1782)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 702)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1278)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1854)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 631)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1207)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1783)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 703)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1279)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1855)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 632)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1208)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1784)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 704)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1280)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1856)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 639)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1215)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1791)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 711)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1287)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1863)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 640)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1216)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1792)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 712)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1288)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1864)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 641)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1217)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1793)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 713)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1289)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1865)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 633)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1209)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1785)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 705)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1281)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1857)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 634)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1210)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1786)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 706)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1282)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1858)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 635)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1211)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1787)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 707)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1283)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1859)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 642)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1218)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1794)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 714)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1290)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1866)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 643)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1219)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1795)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 715)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1291)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1867)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 644)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1220)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1796)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 716)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1292)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1868)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 636)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1212)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1788)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 708)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1284)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1860)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 637)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1213)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1789)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 709)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1285)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1861)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 638)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1214)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1790)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 710)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1286)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1862)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 645)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1221)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1797)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 717)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1293)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1869)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 646)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1222)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1798)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 718)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1294)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1870)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 647)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1223)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1799)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 719)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1295)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 144) + 1871)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
- compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 32) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
}
}
</pre></div>
@@ -2405,7 +1957,7 @@ 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 21.773 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 24.044 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 cd7f9ec50..18faed956 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)
- 9.8660 9.8896 9.8902 9.8183 0.0337
+ 9.5010 9.4928 9.5401 9.4703 0.0291
</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 7efd85249..bb29a1197 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)
- 778.8489 777.8527 784.6227 774.0715 4.3648
+ 767.7877 771.1795 772.1621 760.0214 5.5062
</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 21.708 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.225 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 399a26e91..97546c316 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,30 +600,76 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute} {
- for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
- allocate(compute_3: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- for (j.init: int32, 0, 16) {
- compute_4: Buffer(compute_3, float32, [4096], [])[((((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
- }
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_3: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
+ let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
+ {
+ compute_4: Buffer(compute_3, float32, [1024], [])[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 (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
- for (i.inner: int32, 0, 8) {
- for (j: int32, 0, 16) {
- let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_2: int32 = ((((i.outer.inner*256) + (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[(((i.outer.inner*2048) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 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, 32) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
+ let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_18: int32 = (cse_var_20 + 1)
+ let cse_var_17: int32 = (cse_var_20 + 11)
+ let cse_var_16: int32 = (cse_var_20 + 12)
+ let cse_var_15: int32 = (cse_var_20 + 13)
+ let cse_var_14: int32 = (cse_var_20 + 14)
+ let cse_var_13: int32 = (cse_var_20 + 15)
+ let cse_var_12: int32 = (cse_var_20 + 2)
+ let cse_var_11: int32 = (cse_var_20 + 3)
+ let cse_var_10: int32 = (cse_var_20 + 4)
+ let cse_var_9: int32 = (cse_var_20 + 5)
+ let cse_var_8: int32 = (cse_var_20 + 6)
+ let cse_var_7: int32 = (cse_var_20 + 7)
+ let cse_var_6: int32 = (cse_var_20 + 8)
+ let cse_var_5: int32 = (cse_var_20 + 9)
+ let cse_var_4: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256))
+ let cse_var_3: int32 = (cse_var_20 + 10)
+ {
+ compute_4[cse_var_20] = (compute_4[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_18] = (compute_4[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_12] = (compute_4[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_11] = (compute_4[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_10] = (compute_4[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_9] = (compute_4[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_8] = (compute_4[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_7] = (compute_4[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_6] = (compute_4[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_5] = (compute_4[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_3] = (compute_4[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_17] = (compute_4[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_16] = (compute_4[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_15] = (compute_4[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_14] = (compute_4[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ compute_4[cse_var_13] = (compute_4[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_4 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
+ for (i0.inner: int32, 0, 32) {
for (i1.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
- compute[cse_var_4] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ let cse_var_22: 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_22] = max((compute_4[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_22]), 0f32)
}
}
}
@@ -663,7 +709,7 @@ 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: 1.551 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.815 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 606f799cc..fc8d28e8d 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>00:44.476</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.906</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.606</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.214</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.214</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_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>00:43.050</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>00:00.222</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.211</strong>: <a class="reference internal" href="tune_relay_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>00:00.211</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>00:00.211</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
</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 2d1058aee..8d2b574ca 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.26/42.26 result: MeasureResult(costs=(0.005477762736842105,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6445176601409912, timestamp=1649839267.0031972) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.34/42.34 result: MeasureResult(costs=(0.005467562947368421,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6258668899536133, timestamp=1649846712.621077) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.34 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: 0x00007f33e2367fa2
+ 12: 0x00007f0ffb099fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 143.86/143.86 result: MeasureResult(costs=(0.0016092658000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4409630298614502, timestamp=1649839293.3875308) [('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: 145.05/145.05 result: MeasureResult(costs=(0.001596039126984127,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1495342254638672, timestamp=1649846738.0719416) [('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: 0.002036
+Time cost of this operator: 0.002043
</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 63dc71016..d0e40bc10 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 313.0 98.72 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.134 0.989 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.291 (1, 1, 10, 10, 3) 1 1
-Total_time - 317.057 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.3 98.719 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.131 0.987 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 0.295 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.367 - - - -
</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 82.25 96.867 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 2.049 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.92 1.084 (1, 1, 10, 10, 3) 1 1
-Total_time - 84.91 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 89.8 97.106 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.736 1.877 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.94 1.017 (1, 1, 10, 10, 3) 1 1
+Total_time - 92.476 - - - -
</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 c0882fe9e..c49eff01c 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.664</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:44.708</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:40.576</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>00:03.492</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>00:00.202</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>00:00.198</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.197</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>00:40.629</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>00:03.502</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>00:00.194</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>00:00.193</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>00:00.191</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>
</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 b361a3cf4..6d097d7b7 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>00:08.066</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.098</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:06.127</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>00:01.727</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>00:00.212</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>00:07.192</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>00:01.692</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 36bea1107..2416a5a9f 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>00:05.543</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.776</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.012</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>00:01.130</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>00:00.705</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>00:00.696</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>00:00.307</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>00:02.119</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>00:01.200</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
+<li><p><strong>00:00.737</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
+<li><p><strong>00:00.717</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>00:00.308</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>00:00.238</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>00:00.222</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:00.236</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>00:00.221</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 173fa8c68..f4a060fe5 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -548,7 +548,7 @@ 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/tmp99a8lv2p/input0.cc'\nsource_filename = \"/tmp/tmp99a8lv2p/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
+ attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmp6euf6s_k/input0.cc'\nsource_filename = \"/tmp/tmp6euf6s_k/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 7622d5af6..754fab9b4 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1750,7 +1750,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index c8a9aed36..2216d7012 100644
--- a/docs/reference/api/typedoc/classes/bytestreamreader.html
+++ b/docs/reference/api/typedoc/classes/bytestreamreader.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -141,7 +141,7 @@
<div class="tsd-signature tsd-kind-icon">bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Uint8Array</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
</ul>
</aside>
</section>
@@ -151,7 +151,7 @@
<div class="tsd-signature tsd-kind-icon">offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
</ul>
</aside>
</section>
@@ -168,7 +168,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">Uint8Array</span></h4>
@@ -185,7 +185,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -202,7 +202,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/cachedcallstack.html b/docs/reference/api/typedoc/classes/cachedcallstack.html
index 92693865a..befc59ebb 100644
--- a/docs/reference/api/typedoc/classes/cachedcallstack.html
+++ b/docs/reference/api/typedoc/classes/cachedcallstack.html
@@ -144,7 +144,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L223">memory.ts:223</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -172,7 +172,7 @@
<div class="tsd-signature tsd-kind-icon">temp<wbr>Args<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><a href="../interfaces/disposable.html" class="tsd-signature-type">Disposable</a><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L208">memory.ts:208</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -194,7 +194,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L312">memory.ts:312</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L284">memory.ts:284</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -262,7 +262,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L388">memory.ts:388</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -300,7 +300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L376">memory.ts:376</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -340,7 +340,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L267">memory.ts:267</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -373,7 +373,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L243">memory.ts:243</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -390,7 +390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L321">memory.ts:321</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -422,7 +422,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L252">memory.ts:252</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -444,7 +444,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L359">memory.ts:359</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -470,7 +470,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L342">memory.ts:342</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -496,7 +496,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L350">memory.ts:350</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -522,7 +522,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L326">memory.ts:326</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -548,7 +548,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index b18b6f51f..0f55a8a98 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 4650792c7..f36f23048 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index cf3be63c4..e8fd8492a 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index 34496b4df..f50311afd 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 343ca2b99..0378c6473 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index a4b9bca61..505d00bd3 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index f8076ba2b..6eccd3f67 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 4be550c96..b38d25b46 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 0cf1150dc..ee95c0d24 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/5cfb4bc3d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/61a9269d8/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
... 1747 lines suppressed ...