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 2022/09/02 08:07:18 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@4acddb1d036a5f055f5e62f348b18c5e8562140e)
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 f977749e1 deploying docs (apache/tvm@4acddb1d036a5f055f5e62f348b18c5e8562140e)
f977749e1 is described below
commit f977749e1ee3984790f098973a86d6ec2edca7bb
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Sep 2 08:07:12 2022 +0000
deploying docs (apache/tvm@4acddb1d036a5f055f5e62f348b18c5e8562140e)
---
.../how_to/compile_models/from_darknet.rst.txt | 2 +-
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 2713 +++++++-------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 111 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 8 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 26 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 10 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 14 +-
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 | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 53 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 39 +-
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 | 8 +-
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 | 18 +-
.../tune_conv2d_layer_cuda.html | 2713 +++++++-------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 111 +-
.../tune_with_autotvm/sg_execution_times.html | 8 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 26 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 10 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
121 files changed, 2634 insertions(+), 4645 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index 37c02c752..a6f0e2ef7 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -317,7 +317,7 @@ The process is no different from other examples.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.695 seconds)
+ **Total running time of the script:** ( 1 minutes 3.500 seconds)
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 97810cea6..341043440 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -115,7 +115,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2f5c0f38-d1e0-45cc-b314-3bd3b27fc4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9ed2cb57-beef-4ace-8d6b-e3d923e75800 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
diff --git a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
index 9e687095a..4a1b5866d 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -113,7 +113,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
19%|#9 | 7.99M/41.5M [00:00<00:00, 42.4MB/s]
35%|###4 | 14.3M/41.5M [00:00<00:00, 44.5MB/s]
45%|####4 | 18.6M/41.5M [00:00<00:00, 42.5MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 37.4MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.0MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 39.5MB/s]
100%|##########| 41.5M/41.5M [00:01<00:00, 41.3MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
15%|#5 | 6.33M/41.5M [00:00<00:01, 36.1MB/s]
29%|##9 | 12.2M/41.5M [00:00<00:00, 43.7MB/s]
40%|###9 | 16.6M/41.5M [00:00<00:00, 35.0MB/s]
58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.2MB/s]
77%|#######7 | 32.0M/41.5M [00:00<00:00, 50.8MB/s]
92%|#########2| 38.3M/41.5M [00:00<00:00, 46.4MB/s]
100%|##########| 41.5M/41.5M [00:00<00:00, 44.4MB/s]
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 f650cd156..6b302331d 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -94,7 +94,7 @@ 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]
38%|###8 | 17.0M/44.7M [00:00<00:00, 178MB/s]
76%|#######6 | 34.0M/44.7M [00:00<00:00, 174MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
9%|8 | 3.84M/44.7M [00:00<00:01, 40.1MB/s]
17%|#7 | 7.76M/44.7M [00:00<00:00, 40.7MB/s]
57%|#####7 | 25.6M/44.7M [00:00<00:00, 108MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 120MB/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 af723c105..7363619d6 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -423,7 +423,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.813 seconds)
+ **Total running time of the script:** ( 1 minutes 3.625 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 ee8e26a79..9a5828f21 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:24.015** total execution time for **how_to_compile_models** files:
+**05:08.946** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:08.813 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:03.625 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:06.695 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 01:03.500 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:41.964 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 00:40.483 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:30.046 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:28.508 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:26.766 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:25.593 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:26.009 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.578 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.986 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.949 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.809 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:20.763 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:17.295 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:16.627 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.632 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.318 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index f45f0494e..d62f5a4fd 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
@@ -441,7 +441,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4733 16.3969 17.3753 16.1531 0.3131
+ 16.3642 16.1171 18.4758 16.0554 0.7070
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 fb8b12567..cf692c287 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
@@ -123,7 +123,7 @@ 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 | 5.12M/170M [00:00<00:03, 53.7MB/s]
6%|6 | 10.2M/170M [00:00<00:04, 36.3MB/s]
8%|8 | 14.0M/170M [00:00<00:04, 34.5MB/s]
11%|#1 | 19.3M/170M [00:00<00:03, 41.3MB/s]
15%|#5 | 26.2M/170M [00:00<00:03, 49.5MB/s]
19%|#9 | 32.8M/170M [00:00<00:02, 55.5MB/s]
24%|##3 | 40.6M/170M [00:00<00:02, 63.6MB/s]
28%|##7 | 46.9M/170M [00:00<00:02, 60.2MB/s]
31%|###1 | 52.8M/170M [00:01<00:02, 58.7MB/s]
34%|###4 | 58.5M/170M [00:01<00:03, 36.4MB/s]
37%|###7 | 63.0M/170M [00:01<00:02, 37.4MB/s]
40%|###9 | 67.4M/170M [00:01<00:02, 37.3MB/s]
42%|####2 | 71.4M/170M [00:01<00:02, 37.6MB/s]
44%|####4 | 75.4M/170M [00:01<00:02, 34.4MB/s]
46%|####6 | 79.0M/170M [00:02<00:02, 32.1MB/s]
48%|####8 | 82.2M/170M [00:02<00:02, 31.1MB/s]
51%|##### | 85.8M/170M [00:02<00:02, 32.6MB/
s]
52%|#####2 | 89.0M/170M [00:02<00:02, 28.7MB/s]
54%|#####4 | 91.9M/170M [00:02<00:03, 26.6MB/s]
56%|#####5 | 94.8M/170M [00:02<00:02, 27.0MB/s]
58%|#####7 | 97.9M/170M [00:02<00:02, 28.5MB/s]
59%|#####9 | 101M/170M [00:02<00:02, 28.7MB/s]
61%|###### | 104M/170M [00:02<00:02, 28.8MB/s]
63%|######2 | 106M/170M [00:03<00:02, 28.8MB/s]
64%|######4 | 109M/170M [00:03<00:02, 29.3MB/s]
66%|######6 | 112M/170M [00:03<00:02, 26.4MB/s]
68%|######7 | 115M/170M [00:03<00:02, 28.0MB/s]
70%|######9 | 119M/170M [00:03<00:01, 30.2MB/s]
72%|#######1 | 122M/170M [00:03<00:01, 30.3MB/s]
73%|#######3 | 125M/170M [00:03<00:01, 26.1MB/s]
75%|#######5 | 128M/170M [00:03<00:01, 26.9MB/s]
78%|#######7 | 132M/170M [00:03<00:01, 31.4MB/s]
80%|#######9 | 135M/170M [00:04<00:01, 29.7MB/s]
82%|########1 | 139M/170M [00:04<00:01, 32.4MB/s]
84%|########3 | 142M/170M [00:04<00:00, 33.0MB/s]
86%|########6 | 146M/170M [00:04<00:00, 34.9MB/s]
88%|########8 | 150M/170M [00:04<00:00, 36.2MB/s]
91%|######### | 154M/170M [00:04<00:00, 37.3MB/s]
93%|#########2| 158M/170M [00:04<00:00, 36.8MB/s]
95%|#########4| 161M/170M [00:04<00:00, 33.8MB/s]
98%|#########7| 166M/170M [00:04<00:00, 37.4MB/s]
100%|#########9| 170M/170M [00:05<00:00, 38.6MB/s]
100%|##########| 170M/170M [00:05<00:00, 35.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
12%|#1 | 20.2M/170M [00:00<00:00, 212MB/s]
27%|##7 | 46.7M/170M [00:00<00:00, 250MB/s]
42%|####1 | 70.6M/170M [00:00<00:00, 244MB/s]
57%|#####6 | 96.1M/170M [00:00<00:00, 253MB/s]
71%|####### | 120M/170M [00:00<00:00, 238MB/s]
85%|########5 | 145M/170M [00:00<00:00, 243MB/s]
99%|#########8| 168M/170M [00:00<00:00, 222MB/s]
100%|##########| 170M/170M [00:00<00:00, 233MB/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').
@@ -292,7 +292,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 12.875 seconds)
+ **Total running time of the script:** ( 3 minutes 1.871 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 0eb4447a9..969f2af2b 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -232,7 +232,7 @@ 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]
8%|7 | 1.06M/13.6M [00:00<00:01, 11.0MB/s]
22%|##2 | 3.02M/13.6M [00:00<00:00, 16.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 52.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 146MB/s]
@@ -412,7 +412,7 @@ 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)
- 90.4171 90.3343 95.6119 90.1207 0.5643
+ 90.4819 90.1530 98.2592 89.9635 1.2859
@@ -461,7 +461,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.723 seconds)
+ **Total running time of the script:** ( 1 minutes 11.378 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 77bca16b5..81879b210 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
@@ -439,7 +439,7 @@ 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)
- 122.1707 122.0668 129.6572 120.9341 0.8749
+ 119.7425 119.7052 122.4666 118.7340 0.5297
@@ -476,7 +476,7 @@ 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:** ( 2 minutes 5.507 seconds)
+ **Total running time of the script:** ( 2 minutes 0.139 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 eeb82a7e9..71faa9429 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -255,7 +255,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.686 seconds)
+ **Total running time of the script:** ( 1 minutes 34.409 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 e716b4ae0..5c34369d9 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
@@ -158,7 +158,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5191/132723 [00:00<00:02, 51904.11KB/s]
10%|9 | 12779/132723 [00:00<00:01, 65992.24KB/s]
15%|#5 | 20402/132723 [00:00<00:01, 70663.44KB/s]
21%|##1 | 28027/132723 [00:00<00:01, 72862.01KB/s]
27%|##6 | 35737/132723 [00:00<00:01, 74385.74KB/s]
33%|###2 | 43459/132723 [00:00<00:01, 75344.59KB/s]
39%|###8 | 51173/132723 [00:00<00:01, 75927.36KB/s]
44%|####4 | 58912/132723 [00:00<00:00, 76391.51KB/s]
50%|##### | 66598/132723 [00:00<00:00, 76536.09KB/s]
56%|#####6 | 74344/132723 [00:01<00:00, 76818.55KB/s]
62%|######1 | 82048/132723 [00:01<00:00, 76884.60KB/s]
68%|######7 | 89737/132723 [00:01<00:00, 76874.39KB/s]
73%|#######3 | 97472/132723 [00:01<00:00, 77016.75KB/s]
79%|#######9 | 105174/132723 [00:01<00:00, 76906.11KB/s]
85%|########5 | 112877/132723 [00:01<00:00, 76940.07KB/s]
91%|#########
| 120572/132723 [00:01<00:00, 76613.46KB/s]
97%|#########6| 128283/132723 [00:01<00:00, 76753.32KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75419.83KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|3 | 5052/132723 [00:00<00:02, 50517.52KB/s]
9%|9 | 12267/132723 [00:00<00:01, 63238.03KB/s]
14%|#4 | 18591/132723 [00:00<00:02, 44577.99KB/s]
20%|#9 | 25934/132723 [00:00<00:01, 53662.78KB/s]
25%|##4 | 32889/132723 [00:00<00:01, 57669.14KB/s]
30%|### | 40275/132723 [00:00<00:01, 62584.76KB/s]
36%|###6 | 47987/132723 [00:00<00:01, 66982.49KB/s]
41%|####1 | 54931/132723 [00:00<00:01, 63174.35KB/s]
47%|####7 | 62545/132723 [00:01<00:01, 66883.46KB/s]
52%|#####2 | 69405/132723 [00:01<00:00, 65588.43KB/s]
58%|#####8 | 77043/132723 [00:01<00:00, 68691.95KB/s]
64%|######3 | 84689/132723 [00:01<00:00, 70952.97KB/s]
70%|######9 | 92406/132723 [00:01<00:00, 72778.50KB/s]
75%|#######5 | 99746/132723 [00:01<00:00, 59765.80KB/s]
81%|######## | 107196/132723 [00:01<00:00, 63552.58KB/s]
86%|########6
| 114680/132723 [00:01<00:00, 64474.88KB/s]
92%|#########1| 122073/132723 [00:01<00:00, 67032.61KB/s]
98%|#########7| 129695/132723 [00:02<00:00, 69594.78KB/s]
100%|##########| 132723/132723 [00:02<00:00, 64472.50KB/s]
@@ -241,7 +241,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 46.619 seconds)
+ **Total running time of the script:** ( 2 minutes 41.279 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 38b467176..0bbdc64b9 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
@@ -5,24 +5,24 @@
Computation times
=================
-**12:15.027** total execution time for **how_to_deploy_models** files:
+**11:45.251** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:12.875 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:01.871 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:46.619 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:41.279 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:05.507 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 02:00.139 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:36.686 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:34.409 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:13.723 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:11.378 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:32.192 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.036 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_nano.py` (``deploy_model_on_nano.py``) | 00:23.279 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:23.491 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.853 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.007 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index a78f23fb6..25e1ec516 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
@@ -476,7 +476,7 @@ 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.zip110168ce-5ca5-4266-bd09-0d7497c4930b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipa5bad3a1-8ae2-4332-acf7-357b9d3a97d5 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 2b619aae1..694e2466d 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.688** total execution time for **how_to_extend_tvm** files:
+**00:42.180** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:41.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.922 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.389 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.270 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:01.041 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.980 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.008 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index 9acc13ed2..f09311e79 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
@@ -216,10 +216,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7696us [7696us] (46.82%; 46.82%)
- FoldScaleAxis: 8741us [8us] (53.18%; 53.18%)
- FoldConstant: 8733us [1815us] (53.13%; 99.91%)
- InferType: 6918us [6918us] (42.09%; 79.22%)
+ InferType: 6978us [6978us] (46.53%; 46.53%)
+ FoldScaleAxis: 8019us [6us] (53.47%; 53.47%)
+ FoldConstant: 8014us [1665us] (53.43%; 99.93%)
+ InferType: 6349us [6349us] (42.33%; 79.22%)
@@ -258,10 +258,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 7161us [7161us] (45.68%; 45.68%)
- FoldScaleAxis: 8516us [7us] (54.32%; 54.32%)
- FoldConstant: 8509us [1768us] (54.27%; 99.91%)
- InferType: 6741us [6741us] (43.00%; 79.22%)
+ InferType: 6376us [6376us] (44.78%; 44.78%)
+ FoldScaleAxis: 7863us [5us] (55.22%; 55.22%)
+ FoldConstant: 7858us [1641us] (55.19%; 99.94%)
+ InferType: 6217us [6217us] (43.66%; 79.12%)
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 562097f9a..7d3cf448f 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
@@ -340,7 +340,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.219203 ms
+ Convolution: 33.678519 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 9cbcf31be..8c4e850f3 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
@@ -671,7 +671,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 9.059836 ms
+ conv2d with tensor core: 8.316956 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 cae5cd35d..cb8c26f97 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -143,8 +143,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019549
- Baseline: 3.513594
+ Numpy running time: 0.018890
+ Baseline: 3.439437
@@ -239,7 +239,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.332782
+ Opt1: 0.309559
@@ -342,7 +342,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.347643
+ Opt2: 0.345363
@@ -438,7 +438,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.138471
+ Opt3: 0.117124
@@ -563,7 +563,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111052
+ Opt4: 0.109661
@@ -685,7 +685,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.113193
+ Opt5: 0.111720
@@ -810,7 +810,7 @@ Furthermore, we can also utilize multi-core processors to do the thread-level pa
.. code-block:: none
- Opt6: 0.149446
+ Opt6: 0.147256
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 c20d5de26..73a8b4fd2 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:36.096** total execution time for **how_to_optimize_operators** files:
+**00:34.855** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:33.674 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.663 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.331 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.228 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.092 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.964 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 4b891f8c8..4baa80a37 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**06:27.042** total execution time for **how_to_tune_with_autoscheduler** files:
+**06:12.423** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:32.304 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 03:23.162 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:26.596 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:24.140 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:48.952 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:47.777 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:20.448 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:19.220 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.476 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.073 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:09.267 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:09.051 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index c883873f0..0ef0d0839 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
@@ -240,12 +240,12 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -253,938 +253,470 @@ cooperative fetching, unrolling and operator fusion.
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 17), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 25), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 20), 81)) && (floormod((threadIdx.x_1 + 20), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1274), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1470), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 10)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1666), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 226), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1862), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 134), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2058), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2254), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 238), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2450)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2450), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 146), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2646)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2646), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 18)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2842)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2842), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 250), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3038)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3038), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 158), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3234)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3234), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 22)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3430)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3430), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 262), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3626)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3626), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 170), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3822)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3822), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 26)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4018)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4018), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 274), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4214)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4214), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 182), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4410)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4410), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 30)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 2), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4606)] = kernel[(((((blockIdx.x*73728) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 286), 288), 3)*3)) + (threadIdx.x_2 + 1)) + 69120)]
- }
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 300)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 303)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 360)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 363)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 366)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 369)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 372)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 375)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 378)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 381)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 384)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 387)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 390)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 393)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 396)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 399)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 402)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 405)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 408)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 411)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 414)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 417)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 420)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 423)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 426)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 429)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 432)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 147)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 435)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 150)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 438)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 441)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 156)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 444)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 159)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 447)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 450)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 165)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 453)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 168)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 456)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 459)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 174)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 462)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 177)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 465)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 468)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 183)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 471)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 186)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 474)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 477)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 480)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 483)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 486)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 489)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 492)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 495)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 210)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 498)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 213)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 501)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 504)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 219)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 507)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 222)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 510)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 513)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 228)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 516)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 231)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 519)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 522)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 237)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 525)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 240)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 528)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 531)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 246)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 534)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 249)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 537)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 540)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 255)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 543)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 258)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 546)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 549)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 264)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 552)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 267)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 555)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 558)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 273)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 561)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 276)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 564)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 567)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 282)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 570)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 285)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 573)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 576)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 864)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 579)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 867)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 582)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 870)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 585)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 873)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 588)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 876)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 591)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 879)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 594)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 882)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 597)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 885)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 600)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 888)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 603)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 891)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 606)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 894)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 897)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 900)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 903)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 906)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 909)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 912)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 627)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 915)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 630)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 918)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 633)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 921)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 636)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 924)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 639)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 927)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 642)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 930)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 645)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 933)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 648)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 936)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 651)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 939)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 654)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 942)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 657)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 945)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 660)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 948)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 663)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 951)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 666)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 954)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 669)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 957)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 672)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 960)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 675)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 963)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 678)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 966)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 681)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 969)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 684)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 972)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 687)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 975)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 690)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 978)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 693)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 981)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 696)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 984)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 699)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 987)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 702)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 990)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 705)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 993)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 708)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 996)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 711)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 999)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 714)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1002)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 717)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1005)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 720)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1008)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 723)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1011)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 726)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1014)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 729)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1017)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 732)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1020)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 735)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1023)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 738)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1026)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 741)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1029)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 744)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1032)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 747)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1035)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 750)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1038)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 753)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1041)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 756)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1044)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 759)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1047)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 762)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1050)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 765)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1053)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 768)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1056)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 771)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1059)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 774)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1062)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 777)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1065)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 780)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1068)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 783)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1071)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 786)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1074)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 789)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1077)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 792)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1080)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 795)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1083)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 798)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1086)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 801)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1089)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 804)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1092)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 807)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1095)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 810)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1098)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 813)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 816)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1104)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 819)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 822)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 825)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1113)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 828)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1116)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 831)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 834)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1122)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 837)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1125)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 840)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 843)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1131)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 846)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1134)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 849)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 852)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1140)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 855)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1143)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 858)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1146)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 861)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1149)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1440)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1443)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1446)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1449)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1452)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1455)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1458)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1461)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1464)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1467)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1182)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1470)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1185)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1473)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1188)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1476)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1191)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1479)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1194)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1482)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1197)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1485)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1200)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1488)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1203)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1491)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1206)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1494)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1209)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1497)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1212)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1500)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1215)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1503)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1218)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1506)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1221)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1509)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1224)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1512)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1227)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1515)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1230)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1518)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1233)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1521)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1236)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1524)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1239)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1527)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1242)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1530)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1245)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1533)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1248)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1536)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1251)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1539)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1254)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1542)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1257)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1545)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1260)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1548)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1263)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1551)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1266)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1554)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1269)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1557)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1272)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1560)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1275)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1563)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1278)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1566)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1281)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1569)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1284)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1572)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1287)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1575)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1290)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1578)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1293)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1581)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1296)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1584)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1299)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1587)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1302)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1590)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1305)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1593)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1308)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1596)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1311)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1599)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1314)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1602)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1317)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1605)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1320)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1608)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1323)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1611)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1326)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1614)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1329)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1617)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1332)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1620)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1335)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1623)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1338)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1626)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1341)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1629)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1344)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1632)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1347)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1635)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1350)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1638)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1353)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1641)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1356)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1644)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1359)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1647)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1362)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1650)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1365)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1653)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1368)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1656)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1371)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1659)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1374)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1662)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1377)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1665)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1380)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1668)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1383)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1671)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1386)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1674)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1389)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1677)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1392)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1680)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1395)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1683)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1398)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1686)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1401)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1689)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1404)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1692)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1407)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1695)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1410)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1698)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1413)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1701)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1416)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1704)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1419)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1707)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1422)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1710)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1425)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1713)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1428)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1716)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1431)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1719)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1434)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1722)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1437)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1725)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1728)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2016)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1731)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2019)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1734)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2022)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1737)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2025)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1740)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2028)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1743)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2031)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1746)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2034)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1749)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2037)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1752)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2040)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1755)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2043)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1758)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2046)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1761)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2049)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1764)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2052)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1767)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2055)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1770)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2058)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1773)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2061)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1776)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2064)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1779)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2067)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1782)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2070)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1785)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2073)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1788)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2076)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1791)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2079)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1794)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2082)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1797)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2085)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1800)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2088)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1803)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2091)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1806)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2094)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1809)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2097)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1812)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1815)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2103)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1818)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2106)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1821)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1824)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2112)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1827)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2115)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1830)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1833)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2121)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1836)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2124)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1839)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1842)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2130)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1845)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2133)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1848)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1851)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2139)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1854)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2142)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1857)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2145)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1860)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2148)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1863)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2151)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1866)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2154)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1869)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2157)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1872)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2160)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1875)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2163)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1878)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2166)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1881)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2169)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1884)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2172)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1887)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2175)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1890)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2178)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1893)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2181)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1896)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2184)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1899)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2187)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1902)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2190)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1905)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2193)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1908)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2196)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1911)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2199)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1914)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2202)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1917)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2205)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1920)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2208)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1923)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2211)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1926)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2214)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1929)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2217)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1932)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2220)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1935)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2223)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1938)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2226)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1941)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2229)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1944)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2232)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1947)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2235)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1950)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2238)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1953)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2241)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1956)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2244)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1959)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2247)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1962)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2250)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1965)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2253)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1968)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2256)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1971)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2259)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1974)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2262)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1977)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2265)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1980)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2268)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1983)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2271)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1986)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2274)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1989)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2277)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1992)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2280)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1995)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2283)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1998)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2286)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2001)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2004)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2007)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2010)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2013)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2301)]))
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f3 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*8)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -1239,7 +771,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.327 ms
+ Execution time of this operator: 0.366 ms
@@ -1287,21 +819,21 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+ conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ 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_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
@@ -1309,14 +841,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=8)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=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)
@@ -1336,14 +868,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1361,10 +893,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+ extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1373,861 +905,418 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((9 <= ((((int)threadIdx.x) + 20) % 81)) && (((((int)threadIdx.x) + 20) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + ((((((int)threadIdx.x) + 20) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 214) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 122) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 30)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 226) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
- kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 134) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 42)];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 140) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 238) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 146) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 54)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 250) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
- kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 158) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3234)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3234) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 66)];
- kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 164) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3430)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3430) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 262) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 3626)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3626) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 170) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3822)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3822) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 78)];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4018)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4018) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 274) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
- kernel_shared[(((int)threadIdx.x) + 4214)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4214) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 182) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4410)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4410) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 90)];
- kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 2) {
- kernel_shared[(((int)threadIdx.x) + 4606)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 286) / 3) * 3)) + ((int)threadIdx.x)) + 69121)];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 300)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 303)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 360)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 363)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 366)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 369)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 372)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 375)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 378)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 381)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 384)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 387)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 390)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 393)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 396)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 399)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 402)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 405)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 408)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 411)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 414)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 417)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 420)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 423)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 426)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 429)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 144)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 432)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 147)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 435)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 150)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 438)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 441)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 444)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 447)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 450)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 453)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 456)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 459)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 462)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 465)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 468)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 471)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 474)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 189)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 477)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 480)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 483)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 486)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 489)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 492)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 495)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 210)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 498)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 213)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 501)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 216)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 504)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 219)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 507)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 222)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 510)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 225)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 513)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 228)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 516)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 231)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 519)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 234)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 522)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 237)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 525)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 240)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 528)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 243)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 531)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 246)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 534)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 249)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 252)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 540)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 255)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 543)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 258)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 546)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 261)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 549)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 264)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 552)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 267)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 555)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 270)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 558)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 273)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 561)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 276)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 564)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 279)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 567)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 282)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 570)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 285)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 573)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 576)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 864)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 579)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 867)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 582)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 870)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 585)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 873)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 588)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 876)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 591)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 879)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 594)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 882)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 597)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 885)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 600)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 888)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 603)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 891)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 606)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 894)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 897)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 900)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 903)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 906)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 909)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 912)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 627)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 915)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 630)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 918)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 633)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 921)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 636)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 924)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 639)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 927)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 642)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 930)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 645)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 933)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 648)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 936)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 651)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 939)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 654)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 942)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 657)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 945)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 660)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 948)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 663)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 951)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 666)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 954)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 669)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 957)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 672)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 960)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 675)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 963)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 678)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 966)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 681)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 969)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 684)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 972)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 687)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 975)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 690)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 978)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 693)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 981)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 696)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 984)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 699)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 987)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 702)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 990)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 705)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 993)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 708)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 996)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 711)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 999)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 714)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1002)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 717)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1005)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 720)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1008)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 723)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1011)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 726)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1014)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 729)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1017)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 732)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1020)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 735)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1023)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 738)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1026)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 741)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1029)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 744)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1032)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 747)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1035)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 750)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1038)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 753)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1041)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 756)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1044)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 759)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1047)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 762)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1050)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 765)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1053)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 768)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1056)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 771)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1059)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 774)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1062)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 777)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1065)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 780)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1068)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 783)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1071)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 786)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1074)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 789)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1077)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 792)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1080)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 795)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1083)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 798)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1086)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 801)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1089)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 804)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1092)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 807)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1095)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 810)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1098)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 813)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 816)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1104)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 819)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 822)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 825)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1113)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 828)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1116)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 831)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 834)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1122)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 837)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1125)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 840)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 843)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1131)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 846)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1134)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 849)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 852)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1140)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 855)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1143)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 858)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1146)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 861)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1149)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1440)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1443)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1446)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1449)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1452)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1455)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1458)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1461)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1464)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1467)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1182)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1470)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1185)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1473)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1188)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1476)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1191)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1479)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1194)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1482)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1197)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1485)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1200)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1488)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1203)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1491)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1206)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1494)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1209)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1497)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1212)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1500)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1215)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1503)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1218)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1506)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1221)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1509)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1224)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1512)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1227)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1515)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1230)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1518)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1233)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1521)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1236)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1524)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1239)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1527)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1242)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1530)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1245)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1533)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1248)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1536)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1251)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1539)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1254)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1542)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1257)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1545)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1260)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1548)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1263)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1551)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1266)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1554)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1269)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1557)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1272)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1560)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1275)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1563)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1278)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1566)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1281)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1569)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1284)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1572)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1287)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1575)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1290)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1578)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1293)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1581)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1296)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1584)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1299)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1587)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1302)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1590)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1305)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1593)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1308)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1596)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1311)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1599)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1314)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1602)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1317)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1605)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1320)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1323)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1326)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1329)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1617)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1332)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1620)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1335)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1623)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1338)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1626)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1341)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1629)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1344)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1632)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1347)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1635)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1350)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1638)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1353)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1641)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1356)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1644)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1359)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1647)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1362)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1650)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1365)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1653)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1368)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1656)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1371)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1659)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1374)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1662)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1377)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1665)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1380)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1668)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1383)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1671)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1386)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1674)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1389)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1677)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1392)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1680)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1395)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1683)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1398)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1686)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1401)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1689)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1404)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1692)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1407)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1695)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1410)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1698)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1413)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1701)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1416)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1704)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1419)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1707)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1422)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1710)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1425)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1713)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1428)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1716)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1431)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1719)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1434)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1722)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1437)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1725)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1728)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2016)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1731)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2019)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1734)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2022)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1737)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2025)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1740)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2028)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1743)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2031)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1746)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2034)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1749)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2037)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1752)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2040)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1755)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2043)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1758)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2046)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1761)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2049)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1764)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2052)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1767)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2055)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1770)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2058)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1773)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2061)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1776)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2064)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1779)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2067)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1782)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2070)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1785)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2073)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1788)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2076)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1791)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2079)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1794)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2082)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1797)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2085)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1800)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2088)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1803)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2091)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1806)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2094)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1809)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2097)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1812)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1815)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2103)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1818)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2106)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1821)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1824)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2112)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1827)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2115)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1830)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1833)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2121)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1836)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2124)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1839)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1842)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2130)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1845)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2133)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1848)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1851)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2139)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1854)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2142)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1857)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2145)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1860)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2148)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1863)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2151)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1866)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2154)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1869)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2157)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1872)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2160)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1875)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2163)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1878)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2166)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1881)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2169)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1884)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2172)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1887)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2175)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1890)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2178)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1893)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2181)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2184)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2187)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2190)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1905)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2193)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1908)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2196)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1911)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2199)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1914)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2202)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1917)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2205)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1920)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2208)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1923)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2211)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1926)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2214)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1929)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2217)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1932)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2220)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1935)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2223)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1938)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2226)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1941)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2229)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1944)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2232)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1947)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2235)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1950)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2238)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1953)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2241)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1956)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2244)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1959)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2247)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1962)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2250)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1965)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2253)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1968)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2256)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1971)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2259)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1974)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2262)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1977)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2265)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1980)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2268)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1983)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2271)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1986)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2274)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1989)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2277)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1992)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2280)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1995)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2283)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1998)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2286)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2001)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2004)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2007)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2010)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2013)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2301)]));
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -2289,7 +1378,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 32.304 seconds)
+ **Total running time of the script:** ( 3 minutes 23.162 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 2591d097f..85e8e2bf0 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
@@ -647,7 +647,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.1722 10.1849 10.2133 10.1185 0.0397
+ 10.0090 10.0215 10.0667 9.9388 0.0530
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 35a488e0f..c9ec4b021 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
@@ -666,7 +666,7 @@ 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)
- 768.7073 768.2559 770.1201 767.7458 1.0205
+ 757.7534 757.7726 758.0501 757.4376 0.2504
@@ -694,7 +694,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 26.596 seconds)
+ **Total running time of the script:** ( 1 minutes 24.140 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 ad9dc67d7..2a0f0a210 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
@@ -397,105 +397,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_18: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
- compute[cse_var_18] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_18]), 0f32)
- }
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -551,7 +474,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.812 ms
+ Execution time of this operator: 1.504 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 dd4dec3cb..bf68c242e 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:46.884** total execution time for **how_to_tune_with_autotvm** files:
+**00:45.866** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:46.847 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:45.831 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.006 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
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 478a48015..b73bfc266 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
@@ -1156,8 +1156,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
- No: 9 GFLOPS: 179.14/179.14 result: MeasureResult(costs=(0.0012922816555555555,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458566188812256, timestamp=1662088041.091059) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
- No: 10 GFLOPS: 0.00/179.14 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 80.80/80.80 result: MeasureResult(costs=(0.0028652372571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8589675426483154, timestamp=1662100088.192354) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+ No: 10 GFLOPS: 0.00/80.80 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1280,8 +1280,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
- No: 11 GFLOPS: 260.81/260.81 result: MeasureResult(costs=(0.0008876353535911603,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4380462169647217, timestamp=1662088041.955188) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
- No: 12 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 260.92/260.92 result: MeasureResult(costs=(0.0008872442596685082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.467299461364746, timestamp=1662100089.094708) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+ No: 12 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1404,7 +1404,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
- No: 13 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1527,7 +1527,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
- No: 14 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1650,9 +1650,9 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
- No: 15 GFLOPS: 5.29/260.81 result: MeasureResult(costs=(0.04375010175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8807947635650635, timestamp=1662088046.6638134) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
- No: 16 GFLOPS: 3.36/260.81 result: MeasureResult(costs=(0.0689354325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.713005542755127, timestamp=1662088047.9242866) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
- No: 17 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 5.30/260.92 result: MeasureResult(costs=(0.043695452,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8240137100219727, timestamp=1662100093.6992128) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+ No: 16 GFLOPS: 3.34/260.92 result: MeasureResult(costs=(0.069296861,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.590317249298096, timestamp=1662100094.938638) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+ No: 17 GFLOPS: 0.00/260.92 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
@@ -1670,8 +1670,8 @@ for this template
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
- No: 18 GFLOPS: 28.09/260.81 result: MeasureResult(costs=(0.0082418215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3147664070129395, timestamp=1662088058.9725747) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
- No: 19 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 28.04/260.92 result: MeasureResult(costs=(0.008256552571428571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2937285900115967, timestamp=1662100105.9821656) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+ No: 19 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1794,7 +1794,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
- No: 20 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+ No: 20 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1973,7 +1973,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
- Time cost of this operator: 0.001265
+ Time cost of this operator: 0.001292
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 2f4fb212c..1b25985d7 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
@@ -329,10 +329,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.1 98.705 (1, 2, 10, 10, 3) 2 1 [312.1]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.093 0.978 (1, 6, 10, 10) 1 1 [3.093]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.003 0.317 (1, 1, 10, 10, 3) 1 1 [1.003]
- Total_time - 316.196 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.713 (1, 2, 10, 10, 3) 2 1 [311.1]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.069 0.974 (1, 6, 10, 10) 1 1 [3.069]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.313 (1, 1, 10, 10, 3) 1 1 [0.986]
+ Total_time - 315.156 - - - - -
@@ -398,10 +398,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.562 96.441 (1, 6, 10, 10, 1) 2 1 [81.562]
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 2.367 (1, 6, 10, 10) 1 1 [2.002]
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 1.192 (1, 1, 10, 10, 3) 1 1 [1.008]
- Total_time - 84.572 - - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.312 96.668 (1, 6, 10, 10, 1) 2 1 [79.312]
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 2.159 (1, 6, 10, 10) 1 1 [1.772]
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 1.173 (1, 1, 10, 10, 3) 1 1 [0.962]
+ Total_time - 82.046 - - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 1c50abe5d..6432e16b8 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp1er51kvn/images/random'
+ '/tmp/tmpa0jyw_rn/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp1er51kvn/images/target contains 8144 images
- /tmp/tmp1er51kvn/images/random contains 5000 images
+ /tmp/tmpa0jyw_rn/images/target contains 8144 images
+ /tmp/tmpa0jyw_rn/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 57s - loss: 0.2074 - accuracy: 0.9304 - val_loss: 0.1327 - val_accuracy: 0.9585
+ 328/328 - 56s - loss: 0.2432 - accuracy: 0.9154 - val_loss: 0.1604 - val_accuracy: 0.9520
Epoch 2/3
- 328/328 - 53s - loss: 0.0980 - accuracy: 0.9621 - val_loss: 0.1232 - val_accuracy: 0.9619
+ 328/328 - 53s - loss: 0.0989 - accuracy: 0.9618 - val_loss: 0.1183 - val_accuracy: 0.9645
Epoch 3/3
- 328/328 - 53s - loss: 0.0659 - accuracy: 0.9757 - val_loss: 0.1522 - val_accuracy: 0.9490
+ 328/328 - 53s - loss: 0.0684 - accuracy: 0.9738 - val_loss: 0.1273 - val_accuracy: 0.9619
- <keras.callbacks.History object at 0x7f820c1c4850>
+ <keras.callbacks.History object at 0x7f8cc19f7650>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 46.419 seconds)
+ **Total running time of the script:** ( 5 minutes 8.503 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 448acde5f..98d5a459d 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
@@ -5,16 +5,16 @@
Computation times
=================
-**05:43.632** total execution time for **how_to_work_with_microtvm** files:
+**06:02.441** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:46.419 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 05:08.503 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.532 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.895 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:08.076 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_aot.py` (``micro_aot.py``) | 00:07.688 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.603 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.352 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.001 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 80a00fed6..bff0c5d50 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
@@ -5,14 +5,14 @@
Computation times
=================
-**00:44.891** total execution time for **how_to_work_with_relay** files:
+**00:43.777** total execution time for **how_to_work_with_relay** files:
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:33.679 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_pipeline_executor.py` (``using_pipeline_executor.py``) | 00:31.917 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.618 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.202 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.586 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.650 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.007 | 0.0 MB |
+----------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index acb795bb6..70a6e3bc9 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -261,7 +261,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f81dc1bedd0>
+ <function my_cuda_math_rule at 0x7f8c3b68def0>
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 28da38cb3..819e2461c 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.481** total execution time for **how_to_work_with_schedules** files:
+**00:04.188** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:02.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.925 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.068 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.010 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.574 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.539 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.527 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.107 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.045 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.042 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.029 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.016 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.015 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 10b49d2d5..87eda2f1a 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -347,7 +347,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjevgenwl/input0.cc'\nsource_filename = \"/tmp/tmpjevgenwl/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/tmpxnsrnq72/input0.cc'\nsource_filename = \"/tmp/tmpxnsrnq72/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 ed3a80aaa..895660485 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:23.127** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:22.208** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:23.121 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:22.201 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index c8d92663e..9045a9dc5 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 25.42s!
+ resnet18_v1 inference graph built in 24.17s!
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 fb0bbccb8..9e753a43d 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:348: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 17.42s!
+ yolov3-tiny inference graph built in 16.89s!
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 fc59ed9f9..1e914d01f 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:35.125** total execution time for **topic_vta_tutorials_frontend** files:
+**01:33.161** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.661 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:49.023 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:45.464 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.138 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index cfe13f086..e516c302a 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.390** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.300** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.949 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.890 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.441 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.410 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 55550213e..c15d7b113 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.778** total execution time for **topic_vta_tutorials** files:
+**00:00.728** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.407 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.393 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.371 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.335 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 5fff84024..9b3fb1e8c 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -207,7 +207,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E*E*E
+ *E*E
@@ -333,7 +333,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.643 ms
+ Execution time of this operator: 93.648 ms
@@ -451,7 +451,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.055 seconds)
+ **Total running time of the script:** ( 1 minutes 12.637 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index dd359ce14..6963684d5 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -462,16 +462,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.08/9.08 result: MeasureResult(costs=(0.029560945600000006,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6118500232696533, timestamp=1662086723.6378741) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.52/9.08 result: MeasureResult(costs=(0.10643780939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8589472770690918, timestamp=1662086725.506462) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.60/11.60 result: MeasureResult(costs=(0.0231429856,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5577545166015625, timestamp=1662086726.6088662) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.78/11.60 result: MeasureResult(costs=(0.1511432346,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5453879833221436, timestamp=1662086729.757379) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.63/11.60 result: MeasureResult(costs=(0.07393550219999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3240461349487305, timestamp=1662086731.214074) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.79/11.60 result: MeasureResult(costs=(0.1499543998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.568110227584839, timestamp=1662086733.8204923) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.60 result: MeasureResult(costs=(0.3073258002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.045556306838989, timestamp=1662086739.4816482) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.60/11.60 result: MeasureResult(costs=(0.025315159800000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546350479125977, timestamp=1662086740.0543113) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.76/11.60 result: MeasureResult(costs=(0.15244594360000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.54144287109375, timestamp=1662086742.7160997) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.52/11.60 result: MeasureResult(costs=(0.106664245,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8219544887542725, timestamp=1662086744.595707) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.62/10.62 result: MeasureResult(costs=(0.02527316,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5408856868743896, timestamp=1662098826.6858706) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.81/10.62 result: MeasureResult(costs=(0.09540087480000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6784005165100098, timestamp=1662098828.3762825) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.76/11.76 result: MeasureResult(costs=(0.0228353174,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5652813911437988, timestamp=1662098829.4587834) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.70/11.76 result: MeasureResult(costs=(0.15795107599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.645632266998291, timestamp=1662098832.7061884) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.56/11.76 result: MeasureResult(costs=(0.0754620248,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3421125411987305, timestamp=1662098834.1781847) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.77/11.76 result: MeasureResult(costs=(0.1516094738,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.5654456615448, timestamp=1662098837.35203) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.81/11.76 result: MeasureResult(costs=(0.3317968424,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.431739091873169, timestamp=1662098842.8251426) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 9.86/11.76 result: MeasureResult(costs=(0.027216819600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5781846046447754, timestamp=1662098843.4231288) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.66/11.76 result: MeasureResult(costs=(0.1613756482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.686034679412842, timestamp=1662098846.2302513) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.39/11.76 result: MeasureResult(costs=(0.11213729399999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.9020960330963135, timestamp=1662098848.189188) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 29eccecb2..0f3a24323 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -327,7 +327,7 @@ standard deviation.
.. code-block:: none
- {'mean': 499.802830790004, 'median': 499.61831065002116, 'std': 0.6728640250425578}
+ {'mean': 497.20687912999784, 'median': 496.78902744999505, 'std': 1.2544033598654751}
@@ -563,30 +563,30 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 6.64 s
[Task 1/25] Current/Best: 6.14/ 17.47 GFLOPS | Progress: (8/20) | 9.74 s
[Task 1/25] Current/Best: 11.48/ 22.61 GFLOPS | Progress: (12/20) | 12.24 s
[Task 1/25] Current/Best: 16.39/ 22.68 GFLOPS | Progress: (16/20) | 13.96 s
[Task 1/25] Current/Best: 11.59/ 23.71 GFLOPS | Progress: (20/20) | 15.72 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.16/ 13.39 GFLOPS | Progress: (4/20) | 4.04 s
[Task 2/25] Current/Best: 14.06/ 17.90 GFLOPS | Progress: (8/20) | 5.39 s
[Task 2/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (12/20) | 6.73 s
[Task 2/25] Current/Best: 12.45/ 20.61 GFLOPS | Progress: (16/20) | 8.06 s
[Task 2/25] Current/Best: 18.81/ 20.61 GFLOPS | Progress: (20/20) | 9.73 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.75 GFLOPS | Progress: (4/20) | 5.96 s
[Task 3/25] Current/Best: 15.21/ 16.74 GFLOPS | Progress: (8/20) | 7.91 s
[Task 3/25] Current/Best: 14.87/ 16.74 GFLOPS | Progress: (12/20) | 9.69 s
[Task 3/25] Current/Best: 7.17/ 23.64 GFLOPS | Progress: (16/20) | 11.63 s
[Task 3/25] Current/Best: 12.56/ 23.64 GFLOPS | Progress: (20/20) | 16.27 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.49/ 19.89 GFLOPS | Progress: (4/20) | 2.50 s
[Task 4/25] Current/Best: 6.76/ 19.89 GFLOPS | Progress: (8/20) | 7.37 s
[Task 4/25] Current/Best: 20.93/ 20.93 GFLOPS | Progress: (12/20) | 12.51 s
[Task 4/25] Current/Best: 16.83/ 20.93 GFLOPS | Progress: (16/20) | 15.00 s
[Task 4/25] Current/Best: 12.90/ 20.93 GFLOPS | Progress: (20/20) | 17.09 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.70/ 10.24 GFLOPS | Progress: (4/20) | 2.68 s
[Task 5/25] Current/Best: 11.73/ 13.10 GFLOPS | Progress: (8/20) | 4.75 s
[Task 5/25] Current/Best: 9.69/ 17.91 GFLOPS | Progress: (12/20) | 8.05 s
[Task 5/25] Current/Best: 11.71/ 22.17 GFLOPS | Progress: (16/20) | 9.48 s
[Task 5/25] Current/Best: 11.70/ 22.17 GFLOPS | Progress: (20/20) | 11.44 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.14/ 20.06 GFLOPS | Progress: (4/20) | 4.24 s
[Task 6/25] Current/Best: 18.89/ 20.06 GFLOPS | Progress: (8/20) | 6.02 s
[Task 6/25] Current/Best: 13.08/ 20.06 GFLOPS | Progress: (12/20) | 7.99 s
[Task 6/25] Current/Best: 19.40/ 20.06 GFLOPS | Progress: (16/20) | 10.26 s
[Task 6/25] Current/Best: 3.75/ 20.06 GFLOPS | Progress: (20/20) | 12.79 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.82/ 12.45 GFLOPS | Progress: (4/20) | 3.72 s
[Task 7/25] Current/Best: 19.61/ 21.15 GFLOPS | Progress: (8/20) | 5.28 s
[Task 7/25] Current/Best: 15.22/ 21.15 GFLOPS | Progress: (12/20) | 7.22 s
[Task 7/25] Current/Best: 12.18/ 21.15 GFLOPS | Progress: (16/20) | 9.29 s
[Task 7/25] Current/Best: 6.43/ 21.67 GFLOPS | Progress: (20/20) | 11.77 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.20/ 13.29 GFLOPS | Progress: (4/20) | 3.06 s
[Task 8/25] Current/Best: 9.68/ 13.29 GFLOPS | Progress: (8/20) | 8.30 s
[Task 8/25] Current/Best: 13.58/ 13.74 GFLOPS | Progress: (12/20) | 15.02 s
[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (16/20) | 17.12 s
[Task 8/25] Current/Best: 19.40/ 19.40 GFLOPS | Progress: (20/20) | 24.33 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.16/ 15.55 GFLOPS | Progress: (4/20) | 12.06 s
[Task 9/25] Current/Best: 23.28/ 23.28 GFLOPS | Progress: (8/20) | 13.90 s
[Task 9/25] Current/Best: 8.20/ 23.28 GFLOPS | Progress: (12/20) | 16.49 s
[Task 9/25] Current/Best: 17.76/ 23.28 GFLOPS | Progress: (16/20) | 19.45 s
[Task 9/25] Current/Best: 9.03/ 23.28 GFLOPS | Progress: (20/20) | 28.36 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (4/20) | 2.69 s
[Task 10/25] Current/Best: 15.73/ 17.99 GFLOPS | Progress: (8/20) | 4.37 s
[Task 10/25] Current/Best: 12.63/ 19.18 GFLOPS | Progress: (12/20) | 5.95 s
[Task 10/25] Current/Best: 18.94/ 20.16 GFLOPS | Progress: (16/20) | 7.08 s
[Task 10/25] Current/Best: 8.88/ 20.16 GFLOPS | Progress: (20/20
) | 8.64 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.21/ 18.09 GFLOPS | Progress: (4/20) | 3.49 s
[Task 11/25] Current/Best: 16.52/ 18.09 GFLOPS | Progress: (8/20) | 6.35 s
[Task 11/25] Current/Best: 17.94/ 18.09 GFLOPS | Progress: (12/20) | 8.44 s
[Task 11/25] Current/Best: 13.38/ 20.88 GFLOPS | Progress: (16/20) | 11.38 s
[Task 11/25] Current/Best: 19.41/ 21.58 GFLOPS | Progress: (20/20) | 13.51 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.16 GFLOPS | Progress: (4/20) | 5.99 s
[Task 12/25] Current/Best: 5.31/ 18.16 GFLOPS | Progress: (8/20) | 10.00 s
[Task 12/25] Current/Best: 18.92/ 18.98 GFLOPS | Progress: (12/20) | 11.99 s
[Task 12/25] Current/Best: 13.54/ 18.98 GFLOPS | Progress: (16/20) | 15.00 s
[Task 12/25] Current/Best: 15.26/ 19.15 GFLOPS | Progress: (20/20) | 16.92 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.90/ 17.29 GFLOPS | Progress: (4/20) | 3.85 s
[Task 13/25] Current/Best: 15.62/ 20.64 GFLOPS | Progress: (8/20) | 6.51 s
[Task 13/25] Current/Best: 19.44/ 21.11 GFLOPS | Progress: (12/20) | 9.61 s
[Task 13/25] Current/Best: 12.21/ 21.11 GFLOPS | Progress: (16/20) | 13.13 s
[Task 13/25] Current/Best: 18.40/ 21.11 GFLOPS | Progress: (20/20) | 15.46 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.73/ 13.73 GFLOPS | Progress: (4/20) | 3.53 s
[Task 14/25] Current/Best: 6.10/ 13.73 GFLOPS | Progress: (8/20) | 5.74 s
[Task 14/25] Current/Best: 20.54/ 20.54 GFLOPS | Progress: (12/20) | 8.45 s
[Task 14/25] Current/Best: 16.32/ 20.54 GFLOPS | Progress: (16/20) | 10.15 s Done.
-
[Task 14/25] Current/Best: 17.03/ 20.54 GFLOPS | Progress: (20/20) | 11.92 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.11/ 16.84 GFLOPS | Progress: (4/20) | 2.88 s
[Task 15/25] Current/Best: 14.23/ 17.99 GFLOPS | Progress: (8/20) | 4.15 s
[Task 15/25] Current/Best: 10.33/ 22.25 GFLOPS | Progress: (12/20) | 6.41 s
[Task 15/25] Current/Best: 20.34/ 22.25 GFLOPS | Progress: (16/20) | 10.15 s
[Task 15/25] Current/Best: 9.68/ 22.25 GFLOPS | Progress: (20/20) | 11.18 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (4/20) | 3.14 s
[Task 16/25] Current/Best: 3.02/ 20.39 GFLOPS | Progress: (8/20) | 4.77 s
[Task 16/25] Current/Best: 19.73/ 20.39 GFLOPS | Progress: (12/20) | 6.00 s
[Task 16/25] Current/Best: 17.68/ 20.39 GFLOPS | Progress: (16/20)
| 7.39 s
[Task 16/25] Current/Best: 9.88/ 21.79 GFLOPS | Progress: (20/20) | 9.60 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.52/ 18.19 GFLOPS | Progress: (4/20) | 4.95 s
[Task 17/25] Current/Best: 13.85/ 23.09 GFLOPS | Progress: (8/20) | 7.92 s
[Task 17/25] Current/Best: 18.08/ 23.09 GFLOPS | Progress: (12/20) | 9.99 s
[Task 17/25] Current/Best: 16.44/ 23.09 GFLOPS | Progress: (16/20) | 12.24 s
[Task 17/25] Current/Best: 10.02/ 23.09 GFLOPS | Progress: (20/20) | 14.45 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.53/ 18.00 GFLOPS | Progress: (4/20) | 3.92 s
[Task 18/25] Current/Best: 10.63/ 19.84 GFLOPS | Progress: (8/20) | 7.68 s
[Task 18/25] Current/Best: 19.26/ 19.84 GFLOPS | Progress: (12/20) | 9.63 s
[Task 18/25] Current/Best: 9.76/ 19.84 GFLOPS | Progress: (16/20) | 13.60 s
[Task 18/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (20/20) | 15.15 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.22/ 20.09 GFLOPS | Progress: (4/20) | 6.43 s
[Task 19/25] Current/Best: 2.69/ 20.09 GFLOPS | Progress: (8/20) | 9.75 s
[Task 19/25] Current/Best: 19.17/ 20.69 GFLOPS | Progress: (12/20) | 12.79 s
[Task 19/25] Current/Best: 13.90/ 21.40 GFLOPS | Progress: (16/20) | 15.83 s
[Task 19/25] Current/Best: 2.70/ 22.36 GFLOPS | Progress: (20/20) | 18.64 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.55/ 14.87 GFLOPS | Progress: (4/20) | 3.47 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.43/ 17.43 GFLOPS | Progress: (4/20) | 5.99 s
[Task 1/25] Current/Best: 6.15/ 17.43 GFLOPS | Progress: (8/20) | 9.58 s
[Task 1/25] Current/Best: 11.50/ 22.73 GFLOPS | Progress: (12/20) | 12.11 s
[Task 1/25] Current/Best: 16.44/ 22.73 GFLOPS | Progress: (16/20) | 13.81 s
[Task 1/25] Current/Best: 11.54/ 23.53 GFLOPS | Progress: (20/20) | 15.56 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.28/ 13.18 GFLOPS | Progress: (4/20) | 4.00 s
[Task 2/25] Current/Best: 13.94/ 18.01 GFLOPS | Progress: (8/20) | 5.31 s
[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.63 s
[Task 2/25] Current/Best: 11.65/ 21.13 GFLOPS | Progress: (16/20) | 7.90 s
[Task 2/25] Current/Best: 19.17/ 21.13 GFLOPS | Progress: (20/20) | 9.51 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.82 GFLOPS | Progress: (4/20) | 5.89 s
[Task 3/25] Current/Best: 15.28/ 16.53 GFLOPS | Progress: (8/20) | 7.82 s
[Task 3/25] Current/Best: 14.92/ 16.53 GFLOPS | Progress: (12/20) | 9.57 s
[Task 3/25] Current/Best: 7.18/ 23.70 GFLOPS | Progress: (16/20) | 11.51 s
[Task 3/25] Current/Best: 12.43/ 23.70 GFLOPS | Progress: (20/20) | 16.10 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 20.25 GFLOPS | Progress: (4/20) | 2.45 s
[Task 4/25] Current/Best: 6.80/ 20.25 GFLOPS | Progress: (8/20) | 7.24 s
[Task 4/25] Current/Best: 22.34/ 22.34 GFLOPS | Progress: (12/20) | 12.32 s
[Task 4/25] Current/Best: 17.38/ 22.34 GFLOPS | Progress: (16/20) | 14.74 s
[Task 4/25] Current/Best: 13.44/ 22.34 GFLOPS | Progress: (20/20) | 16.83 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.25/ 10.16 GFLOPS | Progress: (4/20) | 2.66 s
[Task 5/25] Current/Best: 11.47/ 12.57 GFLOPS | Progress: (8/20) | 4.75 s
[Task 5/25] Current/Best: 9.76/ 17.99 GFLOPS | Progress: (12/20) | 7.87 s
[Task 5/25] Current/Best: 11.51/ 22.72 GFLOPS | Progress: (16/20) | 9.29 s
[Task 5/25] Current/Best: 11.88/ 22.72 GFLOPS | Progress: (20/20) | 11.22 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.05/ 20.01 GFLOPS | Progress: (4/20) | 4.19 s
[Task 6/25] Current/Best: 18.85/ 20.01 GFLOPS | Progress: (8/20) | 5.97 s
[Task 6/25] Current/Best: 13.33/ 20.01 GFLOPS | Progress: (12/20) | 7.94 s
[Task 6/25] Current/Best: 20.06/ 20.06 GFLOPS | Progress: (16/20) | 10.19 s
[Task 6/25] Current/Best: 3.72/ 20.06 GFLOPS | Progress: (20/20) | 12.70 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.13/ 12.92 GFLOPS | Progress: (4/20) | 3.60 s
[Task 7/25] Current/Best: 19.82/ 20.97 GFLOPS | Progress: (8/20) | 5.15 s
[Task 7/25] Current/Best: 16.03/ 20.97 GFLOPS | Progress: (12/20) | 7.05 s
[Task 7/25] Current/Best: 12.17/ 20.97 GFLOPS | Progress: (16/20) | 9.11 s
[Task 7/25] Current/Best: 6.33/ 21.66 GFLOPS | Progress: (20/20) | 11.57 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.92/ 13.85 GFLOPS | Progress: (4/20) | 2.97 s
[Task 8/25] Current/Best: 9.21/ 13.85 GFLOPS | Progress: (8/20) | 8.15 s
[Task 8/25] Current/Best: 13.19/ 13.85 GFLOPS | Progress: (12/20) | 14.75 s
[Task 8/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (16/20) | 16.86 s
[Task 8/25] Current/Best: 19.44/ 19.44 GFLOPS | Progress: (20/20) | 24.12 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.50 GFLOPS | Progress: (4/20) | 12.01 s
[Task 9/25] Current/Best: 23.14/ 23.14 GFLOPS | Progress: (8/20) | 13.80 s
[Task 9/25] Current/Best: 8.17/ 23.14 GFLOPS | Progress: (12/20) | 16.40 s
[Task 9/25] Current/Best: 17.83/ 23.14 GFLOPS | Progress: (16/20) | 19.21 s
[Task 9/25] Current/Best: 9.09/ 23.14 GFLOPS | Progress: (20/20) | 28.10 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.17/ 18.17 GFLOPS | Progress: (4/20) | 2.64 s
[Task 10/25] Current/Best: 15.78/ 18.17 GFLOPS | Progress: (8/20) | 4.29 s
[Task 10/25] Current/Best: 12.35/ 18.73 GFLOPS | Progress: (12/20) | 5.86 s
[Task 10/25] Current/Best: 19.01/ 20.28 GFLOPS | Progress: (16/20) | 6.98 s
[Task 10/25] Current/Best: 8.75/ 20.28 GFLOPS | Progress: (20/20
) | 8.55 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.27/ 18.02 GFLOPS | Progress: (4/20) | 3.46 s
[Task 11/25] Current/Best: 17.04/ 18.02 GFLOPS | Progress: (8/20) | 6.30 s
[Task 11/25] Current/Best: 17.03/ 18.02 GFLOPS | Progress: (12/20) | 8.37 s
[Task 11/25] Current/Best: 11.90/ 20.97 GFLOPS | Progress: (16/20) | 11.36 s
[Task 11/25] Current/Best: 16.72/ 21.40 GFLOPS | Progress: (20/20) | 13.51 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.78/ 17.86 GFLOPS | Progress: (4/20) | 5.87 s
[Task 12/25] Current/Best: 5.11/ 17.86 GFLOPS | Progress: (8/20) | 9.88 s
[Task 12/25] Current/Best: 19.14/ 19.14 GFLOPS | Progress: (12/20) | 11.89 s
[Task 12/25] Current/Best: 15.31/ 19.14 GFLOPS | Progress: (16/20) | 14.90 s
[Task 12/25] Current/Best: 15.06/ 19.14 GFLOPS | Progress: (20/20) | 16.86 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.54/ 17.30 GFLOPS | Progress: (4/20) | 3.86 s
[Task 13/25] Current/Best: 16.01/ 20.71 GFLOPS | Progress: (8/20) | 6.52 s
[Task 13/25] Current/Best: 19.60/ 21.43 GFLOPS | Progress: (12/20) | 9.58 s
[Task 13/25] Current/Best: 12.24/ 21.43 GFLOPS | Progress: (16/20) | 13.07 s
[Task 13/25] Current/Best: 18.61/ 21.43 GFLOPS | Progress: (20/20) | 15.40 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.80/ 13.80 GFLOPS | Progress: (4/20) | 3.41 s
[Task 14/25] Current/Best: 6.05/ 13.80 GFLOPS | Progress: (8/20) | 5.64 s
[Task 14/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (12/20) | 8.35 s
[Task 14/25] Current/Best: 16.20/ 19.83 GFLOPS | Progress: (16/20) | 10.02 s Done.
+
[Task 14/25] Current/Best: 16.88/ 19.83 GFLOPS | Progress: (20/20) | 11.76 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.05/ 17.53 GFLOPS | Progress: (4/20) | 2.80 s
[Task 15/25] Current/Best: 13.74/ 17.98 GFLOPS | Progress: (8/20) | 4.18 s
[Task 15/25] Current/Best: 10.33/ 22.24 GFLOPS | Progress: (12/20) | 6.44 s
[Task 15/25] Current/Best: 20.38/ 22.24 GFLOPS | Progress: (16/20) | 9.68 s
[Task 15/25] Current/Best: 9.66/ 22.24 GFLOPS | Progress: (20/20) | 10.70 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.20/ 20.20 GFLOPS | Progress: (4/20) | 3.04 s
[Task 16/25] Current/Best: 3.01/ 20.20 GFLOPS | Progress: (8/20) | 4.67 s
[Task 16/25] Current/Best: 19.10/ 20.20 GFLOPS | Progress: (12/20) | 5.90 s
[Task 16/25] Current/Best: 17.46/ 20.20 GFLOPS | Progress: (16/20) |
7.31 s
[Task 16/25] Current/Best: 9.98/ 21.98 GFLOPS | Progress: (20/20) | 9.49 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.57/ 17.44 GFLOPS | Progress: (4/20) | 4.89 s
[Task 17/25] Current/Best: 14.37/ 23.11 GFLOPS | Progress: (8/20) | 7.83 s
[Task 17/25] Current/Best: 17.09/ 23.11 GFLOPS | Progress: (12/20) | 9.89 s
[Task 17/25] Current/Best: 16.45/ 23.11 GFLOPS | Progress: (16/20) | 12.15 s
[Task 17/25] Current/Best: 10.03/ 23.11 GFLOPS | Progress: (20/20) | 14.33 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.44/ 17.67 GFLOPS | Progress: (4/20) | 3.87 s
[Task 18/25] Current/Best: 10.55/ 19.37 GFLOPS | Progress: (8/20) | 7.63 s
[Task 18/25] Current/Best: 19.14/ 19.37 GFLOPS | Progress: (12/20) | 9.59 s
[Task 18/25] Current/Best: 9.86/ 19.37 GFLOPS | Progress: (16/20) | 13.53 s
[Task 18/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (20/20) | 15.04 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.85/ 20.46 GFLOPS | Progress: (4/20) | 6.22 s
[Task 19/25] Current/Best: 2.69/ 20.46 GFLOPS | Progress: (8/20) | 9.55 s
[Task 19/25] Current/Best: 20.10/ 20.91 GFLOPS | Progress: (12/20) | 12.56 s
[Task 19/25] Current/Best: 15.36/ 20.91 GFLOPS | Progress: (16/20) | 15.58 s
[Task 19/25] Current/Best: 2.69/ 22.76 GFLOPS | Progress: (20/20) | 18.41 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.17/ 15.25 GFLOPS | Progress: (4/20) | 3.41 s Done.
Done.
-
[Task 20/25] Current/Best: 10.15/ 14.87 GFLOPS | Progress: (8/20) | 7.06 s
[Task 20/25] Current/Best: 2.33/ 14.87 GFLOPS | Progress: (12/20) | 11.21 s
[Task 20/25] Current/Best: 12.50/ 14.87 GFLOPS | Progress: (16/20) | 15.06 s
[Task 20/25] Current/Best: 13.20/ 21.52 GFLOPS | Progress: (20/20) | 17.19 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.42 GFLOPS | Progress: (4/20) | 3.41 s
[Task 21/25] Current/Best: 14.38/ 17.42 GFLOPS | Progress: (8/20) | 5.05 s
[Task 21/25] Current/Best: 1.61/ 17.42 GFLOPS | Progress: (12/20) | 7.26 s
[Task 21/25] Current/Best: 17.92/ 17.92 GFLOPS | Progress: (16/20) | 10.87 s
[Task 21/25] Current/Best: 4.46/ 17.92 GFLOPS | Progress: (20/20) | 18.45 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.97 GFLOPS | Progress: (4/20
) | 2.80 s
[Task 22/25] Current/Best: 9.14/ 21.13 GFLOPS | Progress: (8/20) | 4.84 s
[Task 22/25] Current/Best: 19.49/ 21.13 GFLOPS | Progress: (12/20) | 7.27 s
[Task 22/25] Current/Best: 14.82/ 21.13 GFLOPS | Progress: (16/20) | 9.43 s
[Task 22/25] Current/Best: 13.85/ 21.13 GFLOPS | Progress: (20/20) | 11.21 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.33/ 20.03 GFLOPS | Progress: (4/20) | 3.32 s
[Task 23/25] Current/Best: 15.98/ 20.03 GFLOPS | Progress: (8/20) | 6.74 s
[Task 23/25] Current/Best: 20.80/ 20.94 GFLOPS | Progress: (12/20) | 8.63 s
[Task 23/25] Current/Best: 5.79/ 20.94 GFLOPS | Progress: (16/20) | 16.04 s
[Task 23/25] Current/Best: 7.44/ 20.94 GFLOPS | Progress: (20/20) | 20.38 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (4/20) | 11.88 s
[Task 24/25] Current/Best: 2.03/ 8.72 GFLOPS | Progress: (8/20) | 22.94 s
[Task 24/25] Current/Best: 4.00/ 8.72 GFLOPS | Progress: (12/20) | 34.53 s Done.
-
[Task 24/25] Current/Best: 7.19/ 8.72 GFLOPS | Progress: (16/20) | 40.37 s
[Task 24/25] Current/Best: 3.16/ 8.72 GFLOPS | Progress: (20/20) | 46.43 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.53/ 2.64 GFLOPS | Progress: (4/20) | 11.65 s
[Task 25/25] Current/Best: 5.58/ 7.42 GFLOPS | Progress: (8/20) | 23.10 s
[Task 25/25] Current/Best: 5.76/ 7.42 GFLOPS | Progress: (12/20) | 34.63 s
[Task 25/25] Current/Best: 5.75/ 8.91 GFLOPS | Progress: (16/20) | 36.41 s
[Task 25/25] Current/Best: 2.91/ 8.91 GFLOPS | Progress: (20/20) | 47.13 s
+
[Task 20/25] Current/Best: 10.47/ 15.25 GFLOPS | Progress: (8/20) | 6.99 s
[Task 20/25] Current/Best: 2.32/ 16.63 GFLOPS | Progress: (12/20) | 10.99 s
[Task 20/25] Current/Best: 10.96/ 16.63 GFLOPS | Progress: (16/20) | 14.94 s
[Task 20/25] Current/Best: 13.32/ 22.03 GFLOPS | Progress: (20/20) | 17.07 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.64 GFLOPS | Progress: (4/20) | 3.35 s
[Task 21/25] Current/Best: 14.34/ 17.64 GFLOPS | Progress: (8/20) | 5.01 s
[Task 21/25] Current/Best: 1.61/ 17.64 GFLOPS | Progress: (12/20) | 7.16 s
[Task 21/25] Current/Best: 18.05/ 18.05 GFLOPS | Progress: (16/20) | 10.73 s
[Task 21/25] Current/Best: 4.47/ 18.05 GFLOPS | Progress: (20/20) | 18.18 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.90 GFLOPS | Progress: (4/20
) | 2.73 s
[Task 22/25] Current/Best: 8.57/ 21.83 GFLOPS | Progress: (8/20) | 4.78 s
[Task 22/25] Current/Best: 19.94/ 21.83 GFLOPS | Progress: (12/20) | 7.20 s
[Task 22/25] Current/Best: 15.54/ 21.83 GFLOPS | Progress: (16/20) | 9.33 s
[Task 22/25] Current/Best: 14.18/ 21.83 GFLOPS | Progress: (20/20) | 11.07 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.42/ 20.72 GFLOPS | Progress: (4/20) | 3.32 s
[Task 23/25] Current/Best: 16.18/ 20.72 GFLOPS | Progress: (8/20) | 6.70 s
[Task 23/25] Current/Best: 20.86/ 21.46 GFLOPS | Progress: (12/20) | 8.59 s
[Task 23/25] Current/Best: 6.34/ 21.46 GFLOPS | Progress: (16/20) | 15.84 s
[Task 23/25] Current/Best: 7.69/ 21.46 GFLOPS | Progress: (20/20) | 20.10 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.72/ 8.72 GFLOPS | Progress: (4/20) | 11.84 s
[Task 24/25] Current/Best: 3.38/ 8.72 GFLOPS | Progress: (8/20) | 23.10 s
[Task 24/25] Current/Best: 4.18/ 8.72 GFLOPS | Progress: (12/20) | 33.88 s Done.
+
[Task 24/25] Current/Best: 6.63/ 8.72 GFLOPS | Progress: (16/20) | 39.68 s
[Task 24/25] Current/Best: 3.29/ 8.90 GFLOPS | Progress: (20/20) | 45.81 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.50/ 2.90 GFLOPS | Progress: (4/20) | 11.66 s
[Task 25/25] Current/Best: 5.50/ 8.00 GFLOPS | Progress: (8/20) | 22.97 s
[Task 25/25] Current/Best: 5.89/ 8.00 GFLOPS | Progress: (12/20) | 34.48 s
[Task 25/25] Current/Best: 5.84/ 9.47 GFLOPS | Progress: (16/20) | 36.32 s
[Task 25/25] Current/Best: 2.91/ 9.47 GFLOPS | Progress: (20/20) | 46.99 s
@@ -748,8 +748,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 420.08675765000135, 'median': 419.96661005000533, 'std': 1.1592090723124646}
- unoptimized: {'mean': 499.802830790004, 'median': 499.61831065002116, 'std': 0.6728640250425578}
+ optimized: {'mean': 416.73295383000095, 'median': 416.59449945000233, 'std': 1.3970245132080805}
+ unoptimized: {'mean': 497.20687912999784, 'median': 496.78902744999505, 'std': 1.2544033598654751}
@@ -772,7 +772,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 43.302 seconds)
+ **Total running time of the script:** ( 10 minutes 33.364 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 0de761346..66ba075bf 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -282,7 +282,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.962e-07 secs/op
+ 1.185e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 27dd63332..2adefe768 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -263,7 +263,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x22141770)), stage(b, placeholder(b, 0xbaf2570)), 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, 0xc2eada0)), stage(b, placeholder(b, 0xeb348e0)), 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 6b67ad9cc..d20be85ed 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,28 +5,28 @@
Computation times
=================
-**14:01.910** total execution time for **tutorial** files:
+**13:46.674** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:43.302 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:33.364 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:20.055 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:12.637 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.560 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:02.115 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.820 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:31.579 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.721 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.108 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.731 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.969 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.539 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.733 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.174 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.160 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.005 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.001 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_uma.py` (``uma.py``) | 00:00.002 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.001 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 26829ec7b..66f9468b0 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -301,7 +301,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000008
+ Numpy running time: 0.000007
naive: 0.000006
@@ -460,7 +460,7 @@ factor to be the number of threads on your CPU.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vector: 0.000025
+ vector: 0.000027
@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, [(stride: int32*n: int32)], [], type="auto"),
@@ -512,10 +512,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.49372000175208e-06 1.0
- naive 5.8365e-06 0.6871547447756754
- parallel 6.3236e-06 0.7445029973551719
- vector 2.46044e-05 2.8967754994189376
+ numpy 7.082070001160901e-06 1.0
+ naive 5.9761e-06 0.8438352062349554
+ parallel 6.3145e-06 0.891617846048531
+ vector 2.69414e-05 3.804170249035061
@@ -936,7 +936,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018955
+ Numpy running time: 0.019336
@@ -996,7 +996,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.305902
+ none: 3.457124
@@ -1101,7 +1101,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.341165
+ blocking: 0.323563
@@ -1199,7 +1199,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.357151
+ vectorization: 0.349758
@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], []),
@@ -1275,7 +1275,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.132203
+ loop permutation: 0.123231
@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], []),
@@ -1376,7 +1376,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.109336
+ array packing: 0.110740
@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], []),
@@ -1471,7 +1471,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111286
+ block caching: 0.110982
@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], []),
@@ -1559,7 +1559,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:267: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.147921
+ parallelization: 0.147189
@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], []),
@@ -1640,13 +1640,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3059015802000005 1.0
- blocking 0.3411653609 0.10319888618080401
- vectorization 0.3571509433 0.10803435451287485
- loop permutation 0.13220253990000003 0.03998985955655765
- array packing 0.1093361253 0.03307301280680757
- block caching 0.1112863906 0.03366294727783983
- parallelization 0.1479214063 0.044744649140780246
+ none 3.4571235615999996 1.0
+ blocking 0.32356275 0.09359305336782674
+ vectorization 0.3497575717 0.1011701101993959
+ loop permutation 0.1232310203 0.03564553540081372
+ array packing 0.1107396428 0.032032306866332634
+ block caching 0.11098205850000001 0.032102427501502474
+ parallelization 0.14718867949999997 0.04257547550075972
@@ -1688,7 +1688,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 0.560 seconds)
+ **Total running time of the script:** ( 1 minutes 2.115 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 98dfc824f..3976a7714 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-8ca8f24d54d65be552448e5368d879710930711b
+4acddb1d036a5f055f5e62f348b18c5e8562140e
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index f71cf86eb..9a1b2e917 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -574,7 +574,7 @@ class:['truck 0.9266'] left:471 top:83 right:689 bottom:169
class:['bicycle 0.9984'] left:111 top:113 right:577 bottom:447
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.695 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.500 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 1e540040a..f17b24431 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -427,7 +427,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip2f5c0f38-d1e0-45cc-b314-3bd3b27fc4ff from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9ed2cb57-beef-4ace-8d6b-e3d923e75800 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
x (1, 3, 224, 224)
</pre></div>
</div>
diff --git a/docs/how_to/compile_models/from_oneflow.html b/docs/how_to/compile_models/from_oneflow.html
index ecd9ce49f..0f8252399 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -432,13 +432,13 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 19%|#9 | 7.99M/41.5M [00:00<00:00, 42.4MB/s]
- 35%|###4 | 14.3M/41.5M [00:00<00:00, 44.5MB/s]
- 45%|####4 | 18.6M/41.5M [00:00<00:00, 42.5MB/s]
- 58%|#####7 | 24.0M/41.5M [00:00<00:00, 37.4MB/s]
- 77%|#######7 | 32.0M/41.5M [00:00<00:00, 41.0MB/s]
- 92%|#########2| 38.3M/41.5M [00:00<00:00, 39.5MB/s]
-100%|##########| 41.5M/41.5M [00:01<00:00, 41.3MB/s]
+ 15%|#5 | 6.33M/41.5M [00:00<00:01, 36.1MB/s]
+ 29%|##9 | 12.2M/41.5M [00:00<00:00, 43.7MB/s]
+ 40%|###9 | 16.6M/41.5M [00:00<00:00, 35.0MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:00<00:00, 40.2MB/s]
+ 77%|#######7 | 32.0M/41.5M [00:00<00:00, 50.8MB/s]
+ 92%|#########2| 38.3M/41.5M [00:00<00:00, 46.4MB/s]
+100%|##########| 41.5M/41.5M [00:00<00:00, 44.4MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index df3bf1ca6..b127802de 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -414,9 +414,10 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 38%|###8 | 17.0M/44.7M [00:00<00:00, 178MB/s]
- 76%|#######6 | 34.0M/44.7M [00:00<00:00, 174MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 188MB/s]
+ 9%|8 | 3.84M/44.7M [00:00<00:01, 40.1MB/s]
+ 17%|#7 | 7.76M/44.7M [00:00<00:00, 40.7MB/s]
+ 57%|#####7 | 25.6M/44.7M [00:00<00:00, 108MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 120MB/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 9846fa3ae..18dca1da8 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -636,7 +636,7 @@ 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 8.813 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.625 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python 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 f68c6caba..ad0d4c664 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:24.015</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:08.946</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -336,43 +336,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:08.813</p></td>
+<td><p>01:03.625</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>01:06.695</p></td>
+<td><p>01:03.500</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>00:41.964</p></td>
+<td><p>00:40.483</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:30.046</p></td>
+<td><p>00:28.508</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:26.766</p></td>
+<td><p>00:25.593</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:26.009</p></td>
+<td><p>00:24.578</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.986</p></td>
+<td><p>00:22.949</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:20.809</p></td>
+<td><p>00:20.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:17.295</p></td>
+<td><p>00:16.627</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.632</p></td>
+<td><p>00:02.318</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 32f41639d..055826137 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -653,7 +653,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.4733 16.3969 17.3753 16.1531 0.3131
+ 16.3642 16.1171 18.4758 16.0554 0.7070
</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 51391ef55..6961bf16c 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -436,49 +436,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 3%|3 | 5.12M/170M [00:00<00:03, 53.7MB/s]
- 6%|6 | 10.2M/170M [00:00<00:04, 36.3MB/s]
- 8%|8 | 14.0M/170M [00:00<00:04, 34.5MB/s]
- 11%|#1 | 19.3M/170M [00:00<00:03, 41.3MB/s]
- 15%|#5 | 26.2M/170M [00:00<00:03, 49.5MB/s]
- 19%|#9 | 32.8M/170M [00:00<00:02, 55.5MB/s]
- 24%|##3 | 40.6M/170M [00:00<00:02, 63.6MB/s]
- 28%|##7 | 46.9M/170M [00:00<00:02, 60.2MB/s]
- 31%|###1 | 52.8M/170M [00:01<00:02, 58.7MB/s]
- 34%|###4 | 58.5M/170M [00:01<00:03, 36.4MB/s]
- 37%|###7 | 63.0M/170M [00:01<00:02, 37.4MB/s]
- 40%|###9 | 67.4M/170M [00:01<00:02, 37.3MB/s]
- 42%|####2 | 71.4M/170M [00:01<00:02, 37.6MB/s]
- 44%|####4 | 75.4M/170M [00:01<00:02, 34.4MB/s]
- 46%|####6 | 79.0M/170M [00:02<00:02, 32.1MB/s]
- 48%|####8 | 82.2M/170M [00:02<00:02, 31.1MB/s]
- 51%|##### | 85.8M/170M [00:02<00:02, 32.6MB/s]
- 52%|#####2 | 89.0M/170M [00:02<00:02, 28.7MB/s]
- 54%|#####4 | 91.9M/170M [00:02<00:03, 26.6MB/s]
- 56%|#####5 | 94.8M/170M [00:02<00:02, 27.0MB/s]
- 58%|#####7 | 97.9M/170M [00:02<00:02, 28.5MB/s]
- 59%|#####9 | 101M/170M [00:02<00:02, 28.7MB/s]
- 61%|###### | 104M/170M [00:02<00:02, 28.8MB/s]
- 63%|######2 | 106M/170M [00:03<00:02, 28.8MB/s]
- 64%|######4 | 109M/170M [00:03<00:02, 29.3MB/s]
- 66%|######6 | 112M/170M [00:03<00:02, 26.4MB/s]
- 68%|######7 | 115M/170M [00:03<00:02, 28.0MB/s]
- 70%|######9 | 119M/170M [00:03<00:01, 30.2MB/s]
- 72%|#######1 | 122M/170M [00:03<00:01, 30.3MB/s]
- 73%|#######3 | 125M/170M [00:03<00:01, 26.1MB/s]
- 75%|#######5 | 128M/170M [00:03<00:01, 26.9MB/s]
- 78%|#######7 | 132M/170M [00:03<00:01, 31.4MB/s]
- 80%|#######9 | 135M/170M [00:04<00:01, 29.7MB/s]
- 82%|########1 | 139M/170M [00:04<00:01, 32.4MB/s]
- 84%|########3 | 142M/170M [00:04<00:00, 33.0MB/s]
- 86%|########6 | 146M/170M [00:04<00:00, 34.9MB/s]
- 88%|########8 | 150M/170M [00:04<00:00, 36.2MB/s]
- 91%|######### | 154M/170M [00:04<00:00, 37.3MB/s]
- 93%|#########2| 158M/170M [00:04<00:00, 36.8MB/s]
- 95%|#########4| 161M/170M [00:04<00:00, 33.8MB/s]
- 98%|#########7| 166M/170M [00:04<00:00, 37.4MB/s]
-100%|#########9| 170M/170M [00:05<00:00, 38.6MB/s]
-100%|##########| 170M/170M [00:05<00:00, 35.4MB/s]
+ 12%|#1 | 20.2M/170M [00:00<00:00, 212MB/s]
+ 27%|##7 | 46.7M/170M [00:00<00:00, 250MB/s]
+ 42%|####1 | 70.6M/170M [00:00<00:00, 244MB/s]
+ 57%|#####6 | 96.1M/170M [00:00<00:00, 253MB/s]
+ 71%|####### | 120M/170M [00:00<00:00, 238MB/s]
+ 85%|########5 | 145M/170M [00:00<00:00, 243MB/s]
+ 99%|#########8| 168M/170M [00:00<00:00, 222MB/s]
+100%|##########| 170M/170M [00:00<00:00, 233MB/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').
@@ -573,7 +538,7 @@ 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 12.875 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 1.871 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 2bab5a423..7af097d0c 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -480,9 +480,7 @@ 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]
- 8%|7 | 1.06M/13.6M [00:00<00:01, 11.0MB/s]
- 22%|##2 | 3.02M/13.6M [00:00<00:00, 16.5MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 52.7MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 146MB/s]
</pre></div>
</div>
</div>
@@ -571,7 +569,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.4171 90.3343 95.6119 90.1207 0.5643
+ 90.4819 90.1530 98.2592 89.9635 1.2859
</pre></div>
</div>
<div class="admonition note">
@@ -610,7 +608,7 @@ 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 13.723 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.378 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index c952e8d23..16933c4c0 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -573,7 +573,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 122.1707 122.0668 129.6572 120.9341 0.8749
+ 119.7425 119.7052 122.4666 118.7340 0.5297
</pre></div>
</div>
<div class="admonition note">
@@ -601,7 +601,7 @@ 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> ( 2 minutes 5.507 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.139 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 62787c2ae..f6be9d56d 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -509,7 +509,7 @@ 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 36.686 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 34.409 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index e5096de69..fe47f6732 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -441,24 +441,25 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 4%|3 | 5191/132723 [00:00<00:02, 51904.11KB/s]
- 10%|9 | 12779/132723 [00:00<00:01, 65992.24KB/s]
- 15%|#5 | 20402/132723 [00:00<00:01, 70663.44KB/s]
- 21%|##1 | 28027/132723 [00:00<00:01, 72862.01KB/s]
- 27%|##6 | 35737/132723 [00:00<00:01, 74385.74KB/s]
- 33%|###2 | 43459/132723 [00:00<00:01, 75344.59KB/s]
- 39%|###8 | 51173/132723 [00:00<00:01, 75927.36KB/s]
- 44%|####4 | 58912/132723 [00:00<00:00, 76391.51KB/s]
- 50%|##### | 66598/132723 [00:00<00:00, 76536.09KB/s]
- 56%|#####6 | 74344/132723 [00:01<00:00, 76818.55KB/s]
- 62%|######1 | 82048/132723 [00:01<00:00, 76884.60KB/s]
- 68%|######7 | 89737/132723 [00:01<00:00, 76874.39KB/s]
- 73%|#######3 | 97472/132723 [00:01<00:00, 77016.75KB/s]
- 79%|#######9 | 105174/132723 [00:01<00:00, 76906.11KB/s]
- 85%|########5 | 112877/132723 [00:01<00:00, 76940.07KB/s]
- 91%|######### | 120572/132723 [00:01<00:00, 76613.46KB/s]
- 97%|#########6| 128283/132723 [00:01<00:00, 76753.32KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75419.83KB/s]
+ 4%|3 | 5052/132723 [00:00<00:02, 50517.52KB/s]
+ 9%|9 | 12267/132723 [00:00<00:01, 63238.03KB/s]
+ 14%|#4 | 18591/132723 [00:00<00:02, 44577.99KB/s]
+ 20%|#9 | 25934/132723 [00:00<00:01, 53662.78KB/s]
+ 25%|##4 | 32889/132723 [00:00<00:01, 57669.14KB/s]
+ 30%|### | 40275/132723 [00:00<00:01, 62584.76KB/s]
+ 36%|###6 | 47987/132723 [00:00<00:01, 66982.49KB/s]
+ 41%|####1 | 54931/132723 [00:00<00:01, 63174.35KB/s]
+ 47%|####7 | 62545/132723 [00:01<00:01, 66883.46KB/s]
+ 52%|#####2 | 69405/132723 [00:01<00:00, 65588.43KB/s]
+ 58%|#####8 | 77043/132723 [00:01<00:00, 68691.95KB/s]
+ 64%|######3 | 84689/132723 [00:01<00:00, 70952.97KB/s]
+ 70%|######9 | 92406/132723 [00:01<00:00, 72778.50KB/s]
+ 75%|#######5 | 99746/132723 [00:01<00:00, 59765.80KB/s]
+ 81%|######## | 107196/132723 [00:01<00:00, 63552.58KB/s]
+ 86%|########6 | 114680/132723 [00:01<00:00, 64474.88KB/s]
+ 92%|#########1| 122073/132723 [00:01<00:00, 67032.61KB/s]
+ 98%|#########7| 129695/132723 [00:02<00:00, 69594.78KB/s]
+100%|##########| 132723/132723 [00:02<00:00, 64472.50KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -501,7 +502,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 46.619 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 41.279 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 17e4fc118..a424c349c 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>12:15.027</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:45.251</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>03:12.875</p></td>
+<td><p>03:01.871</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:46.619</p></td>
+<td><p>02:41.279</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>02:05.507</p></td>
+<td><p>02:00.139</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:36.686</p></td>
+<td><p>01:34.409</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:13.723</p></td>
+<td><p>01:11.378</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:32.192</p></td>
+<td><p>00:30.036</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_nano.html#sphx-glr-how-to-deploy-models-deploy-model-on-nano-py"><span class="std std-ref">Deploy the Pretrained Model on Jetson Nano</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_nano.py</span></code>)</p></td>
-<td><p>00:23.926</p></td>
+<td><p>00:23.279</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:23.491</p></td>
+<td><p>00:22.853</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 5a6323fe6..12f31f662 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -612,7 +612,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip110168ce-5ca5-4266-bd09-0d7497c4930b 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.zipa5bad3a1-8ae2-4332-acf7-357b9d3a97d5 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 276153ded..4870fd1c5 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.688</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:42.180</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:41.250</p></td>
+<td><p>00:38.922</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.389</p></td>
+<td><p>00:02.270</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:01.041</p></td>
+<td><p>00:00.980</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 667caa660..bbd1755d9 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -512,10 +512,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7696us [7696us] (46.82%; 46.82%)
-FoldScaleAxis: 8741us [8us] (53.18%; 53.18%)
- FoldConstant: 8733us [1815us] (53.13%; 99.91%)
- InferType: 6918us [6918us] (42.09%; 79.22%)
+InferType: 6978us [6978us] (46.53%; 46.53%)
+FoldScaleAxis: 8019us [6us] (53.47%; 53.47%)
+ FoldConstant: 8014us [1665us] (53.43%; 99.93%)
+ InferType: 6349us [6349us] (42.33%; 79.22%)
</pre></div>
</div>
</div>
@@ -537,10 +537,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7161us [7161us] (45.68%; 45.68%)
-FoldScaleAxis: 8516us [7us] (54.32%; 54.32%)
- FoldConstant: 8509us [1768us] (54.27%; 99.91%)
- InferType: 6741us [6741us] (43.00%; 79.22%)
+InferType: 6376us [6376us] (44.78%; 44.78%)
+FoldScaleAxis: 7863us [5us] (55.22%; 55.22%)
+ FoldConstant: 7858us [1641us] (55.19%; 99.94%)
+ InferType: 6217us [6217us] (43.66%; 79.12%)
</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 2540da89c..a2aab5dfa 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -564,7 +564,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.219203 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 33.678519 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index c0c04e18b..b935959cd 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -906,7 +906,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.059836 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.316956 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 4e559438c..bca3017d9 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -461,8 +461,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019549
-Baseline: 3.513594
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018890
+Baseline: 3.439437
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -522,7 +522,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.332782
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.309559
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -589,7 +589,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347643
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.345363
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -650,7 +650,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.138471
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117124
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -733,7 +733,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111052
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.109661
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -819,7 +819,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113193
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111720
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -909,7 +909,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.149446
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147256
</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 043028526..989a34c62 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:36.096</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.855</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:33.674</p></td>
+<td><p>00:32.663</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.331</p></td>
+<td><p>00:01.228</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.092</p></td>
+<td><p>00:00.964</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 0711a9088..fb2ec8e0b 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>06:27.042</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>06:12.423</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -336,27 +336,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>03:32.304</p></td>
+<td><p>03:23.162</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:26.596</p></td>
+<td><p>01:24.140</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:48.952</p></td>
+<td><p>00:47.777</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:20.448</p></td>
+<td><p>00:19.220</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:09.476</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
+<td><p>00:09.073</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:09.267</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
+<td><p>00:09.051</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 579f215a3..8c0b13a87 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
@@ -491,12 +491,12 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2592]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [72]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
@@ -504,938 +504,470 @@ cooperative fetching, unrolling and operator fusion.</p>
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- let cse_var_2: int32 = (rc.outer.outer*1568)
- let cse_var_1: int32 = (rc.outer.outer*288)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2592], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 17), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 34), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 51), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 68), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 4), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 4), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 21), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 21), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 38), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 38), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 55), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 55), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 8), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 8), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 25), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 25), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 42), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 42), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 59), 81)) && (floormod((threadIdx.x_1 + 59), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 59), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 76), 81)) && (floormod((threadIdx.x_1 + 76), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1372), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 76), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1470)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 12), 81)) && (floormod((threadIdx.x_1 + 12), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1470), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 12), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 29), 81)) && (floormod((threadIdx.x_1 + 29), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1568), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 29), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1666)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 46), 81)) && (floormod((threadIdx.x_1 + 46), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1666), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 46), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 7), 9)) && (floormod((threadIdx.x_1 + 63), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1764), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 7), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1862)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 80), 81)) && (floormod((threadIdx.x_1 + 80), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1862), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 16), 81)) && (floormod((threadIdx.x_1 + 16), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1960), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2058)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 33), 81)) && (floormod((threadIdx.x_1 + 33), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2058), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 33), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2156)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 50), 81)) && (floormod((threadIdx.x_1 + 50), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2156), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 50), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2254)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 67), 81)) && (floormod((threadIdx.x_1 + 67), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2254), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 67), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2352)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 3), 81)) && (floormod((threadIdx.x_1 + 3), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2352), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 3), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- pad_temp.shared_1[(threadIdx.x_1 + 2450)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 20), 81)) && (floormod((threadIdx.x_1 + 20), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2450), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_1 < 44), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 2548)] = @tir.if_then_else((((threadIdx.x_1 < 35) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 2548), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 37), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((blockIdx.x*73728) + cse_var_1) + (floordiv((threadIdx.x_2 + 98), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 196), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 294), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 2)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 392), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 490), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 202), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 588), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 4)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 686), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 110), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 784), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 882), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 6)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 980), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 116), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1078), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 214), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1176), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 8)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1274), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 122), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1372), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 220), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1470), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 10)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1568), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 128), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1666), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 226), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1764), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 12)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1862), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 134), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 1960), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 232), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2058), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 14)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2156), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 140), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2254), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 238), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2352), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 16)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2450)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2450), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 146), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2548), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 244), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2646)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2646), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 18)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2744), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 152), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2842)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2842), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 250), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 2940), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 20)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3038)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3038), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 158), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3136), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 256), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3234)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3234), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 22)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3332)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3332), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 164), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3430)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3430), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 262), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3528)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3528), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 24)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3626)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3626), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 170), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3724)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3724), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 268), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3822)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3822), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 26)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 3920)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 3920), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 176), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4018)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4018), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 274), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4116)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4116), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 28)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4214)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4214), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 182), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4312)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4312), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 288), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4410)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4410), 288)*4608)) + cse_var_1) + ((floordiv(threadIdx.x_2, 3) + 30)*3)) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- kernel.shared_1[(threadIdx.x_2 + 4508)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 4508), 288)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 188), 288), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
- if @tir.likely((threadIdx.x_2 < 2), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 4606)] = kernel[(((((blockIdx.x*73728) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 286), 288), 3)*3)) + (threadIdx.x_2 + 1)) + 69120)]
- }
- for (rx.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 288)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 291)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 294)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 297)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 300)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 303)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 306)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 309)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 312)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 315)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 318)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 321)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 324)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 327)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 330)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 333)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 336)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 339)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 342)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 345)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 348)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 351)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 354)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 357)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 360)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 363)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 366)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 369)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 372)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 375)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 378)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 381)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 384)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 387)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 390)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 393)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 396)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 399)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 402)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 405)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 408)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 411)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 414)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 417)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 420)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 423)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 426)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 429)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 144)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 432)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 147)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 435)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 150)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 438)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 153)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 441)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 156)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 444)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 159)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 447)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 162)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 450)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 165)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 453)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 168)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 456)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 171)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 459)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 174)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 462)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 177)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 465)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 180)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 468)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 183)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 471)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 186)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 474)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 189)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 477)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 192)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 480)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 195)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 483)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 198)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 486)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 201)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 489)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 204)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 492)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 207)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 495)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 210)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 498)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 213)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 501)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 216)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 504)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 219)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 507)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 222)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 510)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 225)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 513)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 228)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 516)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 231)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 519)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 234)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 522)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 237)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 525)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 240)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 528)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 243)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 531)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 246)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 534)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 249)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 537)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 252)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 540)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 255)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 543)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 258)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 546)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 261)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 549)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 264)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 552)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 267)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 555)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 270)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 558)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 273)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 561)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 276)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 564)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 279)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 567)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 282)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 570)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 285)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 573)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 576)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 864)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 579)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 867)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 582)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 870)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 585)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 873)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 588)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 876)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 591)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 879)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 594)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 882)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 597)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 885)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 600)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 888)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 603)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 891)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 606)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 894)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 609)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 897)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 612)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 900)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 615)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 903)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 618)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 906)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 621)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 909)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 624)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 912)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 627)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 915)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 630)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 918)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 633)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 921)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 636)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 924)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 639)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 927)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 642)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 930)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 645)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 933)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 648)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 936)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 651)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 939)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 654)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 942)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 657)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 945)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 660)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 948)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 663)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 951)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 666)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 954)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 669)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 957)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 672)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 960)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 675)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 963)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 678)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 966)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 681)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 969)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 684)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 972)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 687)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 975)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 690)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 978)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 693)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 981)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 696)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 984)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 699)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 987)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 702)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 990)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 705)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 993)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 708)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 996)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 711)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 999)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 714)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1002)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 717)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1005)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 720)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1008)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 723)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1011)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 726)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1014)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 729)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1017)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 732)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1020)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 735)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1023)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 738)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1026)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 741)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1029)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 744)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1032)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 747)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1035)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 750)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1038)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 753)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1041)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 756)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1044)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 759)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1047)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 762)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1050)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 765)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1053)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 768)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1056)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 771)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1059)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 774)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1062)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 777)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1065)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 780)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1068)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 783)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1071)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 786)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1074)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 789)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1077)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 792)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1080)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 795)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1083)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 798)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1086)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 801)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1089)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 804)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1092)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 807)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1095)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 810)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1098)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 813)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1101)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 816)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1104)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 819)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1107)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 822)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1110)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 825)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1113)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 828)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1116)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 831)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1119)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 834)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1122)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 837)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1125)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 840)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1128)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 843)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1131)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 846)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1134)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 849)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1137)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 852)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1140)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 855)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1143)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 858)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1146)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 861)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1149)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1152)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1440)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1155)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1443)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1158)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1446)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1161)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1449)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1164)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1452)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1167)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1455)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1170)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1458)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1173)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1461)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1176)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1464)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1179)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1467)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1182)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1470)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1185)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1473)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1188)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1476)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1191)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1479)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1194)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1482)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1197)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1485)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1200)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1488)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1203)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1491)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1206)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1494)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1209)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1497)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1212)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1500)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1215)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1503)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1218)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1506)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1221)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1509)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1224)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1512)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1227)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1515)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1230)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1518)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1233)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1521)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1236)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1524)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1239)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1527)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1242)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1530)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1245)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1533)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1248)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1536)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1251)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1539)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1254)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1542)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1257)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1545)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1260)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1548)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1263)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1551)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1266)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1554)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1269)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1557)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1272)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1560)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1275)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1563)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1278)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1566)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1281)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1569)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1284)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1572)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1287)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1575)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1290)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1578)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1293)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1581)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1296)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1584)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1299)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1587)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1302)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1590)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1305)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1593)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1308)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1596)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1311)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1599)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1314)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1602)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1317)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1605)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1320)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1608)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1323)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1611)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1326)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1614)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1329)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1617)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1332)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1620)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1335)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1623)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1338)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1626)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1341)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1629)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1344)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1632)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1347)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1635)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1350)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1638)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1353)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1641)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1356)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1644)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1359)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1647)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1362)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1650)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1365)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1653)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1368)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1656)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1371)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1659)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1374)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1662)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1377)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1665)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1380)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1668)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1383)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1671)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1386)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1674)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1389)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1677)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1392)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1680)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1395)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1683)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1398)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1686)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1401)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1689)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1404)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1692)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1407)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1695)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1410)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1698)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1413)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1701)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1416)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1704)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1419)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1707)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1422)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1710)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1425)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1713)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1428)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1716)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1431)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1719)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1434)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1722)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1437)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1725)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1728)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2016)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1731)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2019)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1734)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2022)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1737)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2025)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1740)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2028)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1743)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2031)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1746)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2034)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1749)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2037)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1752)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2040)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1755)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2043)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1758)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2046)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1761)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2049)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1764)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2052)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1767)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2055)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1770)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2058)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1773)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2061)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1776)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2064)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1779)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2067)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1782)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2070)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1785)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2073)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1788)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2076)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1791)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2079)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1794)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2082)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1797)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2085)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1800)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2088)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1803)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2091)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1806)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2094)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1809)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2097)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1812)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2100)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1815)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2103)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1818)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2106)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1821)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2109)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1824)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2112)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1827)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2115)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1830)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2118)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1833)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2121)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1836)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2124)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1839)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2127)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1842)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2130)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1845)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2133)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1848)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2136)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1851)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2139)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1854)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2142)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1857)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2145)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1860)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2148)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1863)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2151)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1866)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2154)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1869)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2157)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1872)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1296)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2160)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1875)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1305)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2163)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1878)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1314)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2166)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1881)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1377)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2169)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1884)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2172)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1887)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1395)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2175)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1890)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1458)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2178)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1893)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1467)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2181)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1896)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1476)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2184)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1899)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1539)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2187)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1902)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1548)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2190)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1905)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1557)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2193)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1908)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1620)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2196)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1911)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1629)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2199)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1914)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2202)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1917)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2205)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1920)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1710)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2208)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1923)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1719)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2211)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1926)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1782)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2214)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1929)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1791)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2217)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1932)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1800)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2220)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1935)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1863)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2223)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1938)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1872)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2226)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1941)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1881)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2229)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1944)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1944)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2232)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1947)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2235)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1950)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 1962)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2238)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1953)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2025)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2241)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1956)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2034)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2244)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1959)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2043)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2247)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1962)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2106)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2250)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1965)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2115)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2253)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1968)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2124)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2256)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1971)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2187)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2259)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1974)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2196)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2262)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1977)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2205)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2265)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1980)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2268)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2268)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1983)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2277)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2271)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1986)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2286)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2274)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1989)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2349)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2277)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1992)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2358)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2280)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1995)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2367)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2283)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 1998)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2430)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2286)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2001)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2439)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2289)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2004)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2448)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2292)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2007)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2511)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2295)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2010)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2520)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2298)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2013)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 2529)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*2304) + rx.outer.inner) + 2301)]))
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ for (ry.outer.outer: int32, 0, 3) {
+ let cse_var_2: int32 = (rc.outer.outer*72)
+ let cse_var_1: int32 = (ry.outer.outer*3)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64 {
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [72], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1*4), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 1), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 2), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0 [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 18), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod(blockIdx.x, 7))) && ((ry.outer.outer + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((((rc.outer.outer*392) + (floordiv(((threadIdx.x_1*4) + 3), 9)*49)) + (ry.outer.outer*7)) + (floormod(blockIdx.x, 7)*7)) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0 [...]
+ }
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 64), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 128), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 256), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 320), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 448), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 512), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 640), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 704), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 832), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 896), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1024), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1088), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1216), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1280), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1408), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1472), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1600), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1664), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 331776)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1792), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1856), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 1984), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2048), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 405504)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2176), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2240), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2368), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2432), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 479232)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2560), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2624), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2752), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2816), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[(((((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 24), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 552960)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 2944), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 64;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*589824) + (floordiv((threadIdx.x_2 + 3008), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 24), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*48) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*48) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*48) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*48) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 37)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*48) + 38)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*48) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 42)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 43)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*48) + 47)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*48) + 44)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*48) + 47)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*8)) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 2) {
+ for (i3.inner: int32, 0, 7) {
+ compute[(((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + i3.inner)] = max((conv2d_nchw_1[((i1.inner*7) + i3.inner)] + bias[(((floordiv(blockIdx.x, 7)*128) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ }
}
}
}
@@ -1472,7 +1004,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.327 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.366 ms
</pre></div>
</div>
</div>
@@ -1501,21 +1033,21 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
+conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=64)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_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_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+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_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
@@ -1523,14 +1055,14 @@ s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, 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=8)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=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)
@@ -1550,14 +1082,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1575,10 +1107,10 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2592];
- __shared__ float kernel_shared[4608];
+extern "C" __global__ void __launch_bounds__(64) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[72];
+ __shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
@@ -1587,861 +1119,418 @@ extern "C" __global__ void __launch_bounds__(98) default_function_kern
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1274)] = (((((9 <= ((((int)threadIdx.x) + 59) % 81)) && (((((int)threadIdx.x) + 59) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((9 <= ((((int)threadIdx.x) + 76) % 81)) && (((((int)threadIdx.x) + 76) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 81) * 49)) + ((((((int)threadIdx.x) + 76) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1470)] = (((((9 <= ((((int)threadIdx.x) + 12) % 81)) && (((((int)threadIdx.x) + 12) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1470) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((9 <= ((((int)threadIdx.x) + 29) % 81)) && (((((int)threadIdx.x) + 29) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 81) * 49)) + ((((((int)threadIdx.x) + 29) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1666)] = (((((9 <= ((((int)threadIdx.x) + 46) % 81)) && (((((int)threadIdx.x) + 46) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1666) / 81) * 49)) + ((((((int)threadIdx.x) + 46) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) / 9) + 7) % 9)) && (((((int)threadIdx.x) + 63) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1764) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 7) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1862)] = (((((9 <= ((((int)threadIdx.x) + 80) % 81)) && (((((int)threadIdx.x) + 80) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1862) / 81) * 49)) + ((((((int)threadIdx.x) + 80) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((9 <= ((((int)threadIdx.x) + 16) % 81)) && (((((int)threadIdx.x) + 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 81) * 49)) + ((((((int)threadIdx.x) + 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2058)] = (((((9 <= ((((int)threadIdx.x) + 33) % 81)) && (((((int)threadIdx.x) + 33) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2058) / 81) * 49)) + ((((((int)threadIdx.x) + 33) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2156)] = (((((9 <= ((((int)threadIdx.x) + 50) % 81)) && (((((int)threadIdx.x) + 50) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2156) / 81) * 49)) + ((((((int)threadIdx.x) + 50) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2254)] = (((((9 <= ((((int)threadIdx.x) + 67) % 81)) && (((((int)threadIdx.x) + 67) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2254) / 81) * 49)) + ((((((int)threadIdx.x) + 67) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2352)] = (((((9 <= ((((int)threadIdx.x) + 3) % 81)) && (((((int)threadIdx.x) + 3) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2352) / 81) * 49)) + ((((((int)threadIdx.x) + 3) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 2450)] = (((((9 <= ((((int)threadIdx.x) + 20) % 81)) && (((((int)threadIdx.x) + 20) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2450) / 81) * 49)) + ((((((int)threadIdx.x) + 20) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 44) {
- pad_temp_shared[(((int)threadIdx.x) + 2548)] = ((((((int)threadIdx.x) < 35) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 2548) / 81) * 49)) + (((((int)threadIdx.x) + 37) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + ((int)threadIdx.x))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 98) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 196) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 6)];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 104) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 202) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 12)];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 110) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 208) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 18)];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 116) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 214) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 24)];
- kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 122) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 220) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 30)];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 128) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 226) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 36)];
- kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 134) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 232) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 42)];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 140) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 238) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2352) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 48)];
- kernel_shared[(((int)threadIdx.x) + 2450)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2450) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 146) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2548) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 244) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2646)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2646) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 54)];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2744) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 152) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2842)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2842) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 250) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2940) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 60)];
- kernel_shared[(((int)threadIdx.x) + 3038)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3038) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 158) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3136) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 256) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3234)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3234) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 66)];
- kernel_shared[(((int)threadIdx.x) + 3332)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3332) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 164) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3430)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3430) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 262) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3528)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3528) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 72)];
- kernel_shared[(((int)threadIdx.x) + 3626)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3626) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 170) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3724)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3724) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 268) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 3822)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3822) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 78)];
- kernel_shared[(((int)threadIdx.x) + 3920)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 3920) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 176) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4018)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4018) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 274) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4116)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4116) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 84)];
- kernel_shared[(((int)threadIdx.x) + 4214)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4214) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 182) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4312)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4312) / 288) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 280) % 288) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 4410)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4410) / 288) * 4608)) + (rc_outer_outer * 288)) + ((int)threadIdx.x)) + 90)];
- kernel_shared[(((int)threadIdx.x) + 4508)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 4508) / 288) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 188) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 2) {
- kernel_shared[(((int)threadIdx.x) + 4606)] = kernel[(((((((int)blockIdx.x) * 73728) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 286) / 3) * 3)) + ((int)threadIdx.x)) + 69121)];
- }
- __syncthreads();
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 288)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 291)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 294)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 297)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 300)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 303)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 306)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 309)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 312)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 315)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 318)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 321)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 324)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 327)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 330)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 333)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 336)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 339)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 342)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 345)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 348)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 351)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 354)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 357)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 360)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 363)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 366)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 369)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 372)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 375)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 378)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 381)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 384)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 387)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 390)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 393)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 396)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 399)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 402)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 405)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 408)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 411)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 414)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 417)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 420)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 423)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 426)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 429)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 144)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 432)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 147)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 435)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 150)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 438)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 153)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 441)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 156)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 444)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 159)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 447)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 162)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 450)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 165)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 453)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 168)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 456)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 171)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 459)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 174)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 462)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 177)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 465)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 180)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 468)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 183)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 471)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 186)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 474)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 189)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 477)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 192)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 480)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 195)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 483)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 198)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 486)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 201)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 489)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 204)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 492)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 207)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 495)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 210)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 498)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 213)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 501)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 216)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 504)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 219)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 507)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 222)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 510)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 225)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 513)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 228)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 516)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 231)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 519)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 234)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 522)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 237)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 525)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 240)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 528)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 243)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 531)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 246)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 534)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 249)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 537)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 252)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 540)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 255)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 543)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 258)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 546)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 261)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 549)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 264)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 552)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 267)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 555)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 270)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 558)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 273)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 561)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 276)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 564)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 279)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 567)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 282)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 570)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 285)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 573)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 576)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 864)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 579)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 867)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 582)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 870)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 585)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 873)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 588)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 876)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 591)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 879)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 594)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 882)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 597)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 885)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 600)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 888)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 603)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 891)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 606)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 894)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 609)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 897)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 612)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 900)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 615)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 903)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 618)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 906)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 621)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 909)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 624)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 912)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 627)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 915)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 630)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 918)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 633)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 921)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 636)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 924)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 639)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 927)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 642)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 930)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 645)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 933)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 648)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 936)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 651)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 939)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 654)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 942)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 657)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 945)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 660)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 948)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 663)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 951)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 666)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 954)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 669)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 957)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 672)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 960)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 675)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 963)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 678)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 966)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 681)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 969)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 684)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 972)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 687)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 975)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 690)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 978)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 693)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 981)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 696)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 984)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 699)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 987)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 702)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 990)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 705)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 993)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 708)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 996)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 711)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 999)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 714)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1002)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 717)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1005)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 720)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1008)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 723)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1011)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 726)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1014)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 729)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1017)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 732)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1020)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 735)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1023)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 738)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1026)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 741)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1029)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 744)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1032)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 747)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1035)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 750)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1038)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 753)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1041)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 756)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1044)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 759)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1047)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 762)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1050)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 765)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1053)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 768)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1056)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 771)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1059)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 774)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1062)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 777)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1065)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 780)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1068)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 783)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1071)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 786)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1074)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 789)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1077)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 792)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1080)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 795)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1083)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 798)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1086)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 801)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1089)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 804)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1092)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 807)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1095)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 810)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1098)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 813)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1101)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 816)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1104)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 819)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1107)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 822)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1110)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 825)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1113)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 828)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1116)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 831)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1119)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 834)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1122)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 837)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1125)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 840)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1128)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 843)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1131)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 846)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1134)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 849)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1137)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 852)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1140)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 855)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1143)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 858)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1146)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 861)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1149)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1152)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1440)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1155)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1443)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1158)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1446)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1161)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1449)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1164)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1452)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1167)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1455)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1170)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1458)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1173)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1461)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1176)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1464)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1179)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1467)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1182)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1470)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1185)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1473)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1188)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1476)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1191)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1479)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1194)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1482)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1197)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1485)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1200)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1488)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1203)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1491)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1206)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1494)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1209)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1497)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1212)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1500)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1215)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1503)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1218)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1506)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1221)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1509)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1224)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1512)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1227)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1515)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1230)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1518)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1233)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1521)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1236)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1524)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1239)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1527)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1242)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1530)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1245)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1533)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1248)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1536)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1251)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1539)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1254)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1542)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1257)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1545)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1260)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1548)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1263)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1551)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1266)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1554)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1269)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1557)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1272)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1560)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1275)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1563)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1278)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1566)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1281)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1569)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1284)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1572)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1287)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1575)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1290)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1578)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1293)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1581)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1296)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1584)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1299)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1587)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1302)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1590)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1305)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1593)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1308)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1596)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1311)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1599)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1314)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1602)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1317)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1605)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1320)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1608)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1323)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1611)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1326)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1614)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1329)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1617)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1332)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1620)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1335)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1623)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1338)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1626)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1341)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1629)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1344)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1632)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1347)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1635)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1350)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1638)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1353)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1641)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1356)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1644)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1359)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1647)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1362)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1650)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1365)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1653)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1368)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1656)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1371)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1659)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1374)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1662)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1377)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1665)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1380)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1668)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1383)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1671)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1386)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1674)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1389)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1677)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1392)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1680)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1395)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1683)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1398)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1686)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1401)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1689)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1404)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1692)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1407)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1695)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1410)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1698)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1413)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1701)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1416)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1704)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1419)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1707)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1422)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1710)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1425)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1713)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1428)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1716)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1431)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1719)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1434)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1722)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1437)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1725)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1728)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2016)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1731)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2019)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1734)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2022)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1737)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2025)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1740)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2028)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1743)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2031)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1746)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2034)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1749)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2037)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1752)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2040)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1755)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2043)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1758)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2046)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1761)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2049)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1764)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2052)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1767)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2055)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1770)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2058)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1773)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2061)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1776)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2064)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1779)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2067)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1782)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2070)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1785)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2073)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1788)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2076)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1791)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2079)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1794)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2082)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1797)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2085)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1800)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2088)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1803)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2091)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1806)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2094)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1809)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2097)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1812)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2100)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1815)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2103)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1818)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2106)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1821)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2109)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1824)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2112)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1827)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2115)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1830)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2118)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1833)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2121)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1836)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2124)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1839)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2127)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1842)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2130)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1845)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2133)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1848)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2136)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1851)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2139)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1854)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2142)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1857)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2145)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1860)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2148)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1863)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2151)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1866)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2154)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1869)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2157)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1872)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1296)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2160)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1875)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1305)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2163)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1878)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1314)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2166)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1881)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1377)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2169)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1884)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2172)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1887)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1395)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2175)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1890)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1458)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2178)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1893)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1467)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2181)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1896)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1476)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2184)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1899)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1539)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2187)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1902)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1548)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2190)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1905)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1557)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2193)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1908)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1620)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2196)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1911)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1629)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2199)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1914)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2202)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1917)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2205)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1920)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1710)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2208)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1923)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1719)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2211)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1926)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1782)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2214)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1929)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1791)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2217)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1932)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1800)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2220)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1935)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1863)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2223)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1938)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1872)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2226)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1941)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1881)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2229)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1944)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1944)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2232)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1947)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2235)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1950)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 1962)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2238)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1953)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2025)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2241)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1956)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2034)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2244)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1959)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2043)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2247)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1962)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2106)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2250)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1965)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2115)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2253)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1968)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2124)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2256)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1971)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2187)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2259)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1974)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2196)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2262)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1977)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2205)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2265)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1980)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2268)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2268)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1983)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2277)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2271)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1986)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2286)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2274)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1989)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2349)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2277)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1992)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2358)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2280)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1995)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2367)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2283)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 1998)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2430)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2286)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2001)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2439)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2289)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2004)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2448)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2292)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2007)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2511)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2295)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2010)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2520)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2298)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2013)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 2529)] * kernel_shared[((((((int)threadIdx.x) / 49) * 2304) + rx_outer_inner) + 2301)]));
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
+ for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
+ __syncthreads();
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) * 4) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
+ }
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 48) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 48) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 48) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 48) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 37)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 48) + 38)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 48) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 42)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 43)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 48) + 44)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 48) + 47)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 8)) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -2478,7 +1567,7 @@ 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> ( 3 minutes 32.304 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 23.162 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 25fda6126..956eb560f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -906,7 +906,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.1722 10.1849 10.2133 10.1185 0.0397
+ 10.0090 10.0215 10.0667 9.9388 0.0530
</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 152be884e..1c5b5b6b0 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -925,7 +925,7 @@ 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)
- 768.7073 768.2559 770.1201 767.7458 1.0205
+ 757.7534 757.7726 758.0501 757.4376 0.2504
</pre></div>
</div>
</div>
@@ -947,7 +947,7 @@ 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 26.596 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 24.140 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 155a95613..7e2be1a8e 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -625,105 +625,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_17: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_2: int32 = ((i.outer.inner*512) + (i.inner*16))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16))]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_3: int32 = (((i.outer.inner*512) + (i.inner*16)) + 1)
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 1)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_4: int32 = (((i.outer.inner*512) + (i.inner*16)) + 2)
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 2)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_5: int32 = (((i.outer.inner*512) + (i.inner*16)) + 3)
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 3)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_6: int32 = (((i.outer.inner*512) + (i.inner*16)) + 4)
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 4)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_7: int32 = (((i.outer.inner*512) + (i.inner*16)) + 5)
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 5)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_8: int32 = (((i.outer.inner*512) + (i.inner*16)) + 6)
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 6)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_9: int32 = (((i.outer.inner*512) + (i.inner*16)) + 7)
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 7)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_10: int32 = (((i.outer.inner*512) + (i.inner*16)) + 8)
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 8)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_11: int32 = (((i.outer.inner*512) + (i.inner*16)) + 9)
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 9)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_12: int32 = (((i.outer.inner*512) + (i.inner*16)) + 10)
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 10)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_13: int32 = (((i.outer.inner*512) + (i.inner*16)) + 11)
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 11)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_14: int32 = (((i.outer.inner*512) + (i.inner*16)) + 12)
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 12)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_15: int32 = (((i.outer.inner*512) + (i.inner*16)) + 13)
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 13)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_16: int32 = (((i.outer.inner*512) + (i.inner*16)) + 14)
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 14)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- }
- if @tir.likely((elem_idx < (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])), dtype=bool) {
- let cse_var_17: int32 = (((i.outer.inner*512) + (i.inner*16)) + 15)
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + (elem_idx*16)) + 15)]*max(placeholder[(((i.outer.inner*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_18: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
- compute[cse_var_18] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_18]), 0f32)
- }
+ for (i0.inner: int32, 0, 16) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -761,7 +684,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.812 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.504 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 12c9dcd39..3717f0c14 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:46.884</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:45.866</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:46.847</p></td>
+<td><p>00:45.831</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><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></td>
-<td><p>00:00.006</p></td>
+<td><p>00:00.005</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></td>
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 dca82bd73..2cfaf432f 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1436,8 +1436,8 @@ No: 8 GFLOPS: 0.00/0.00 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 1, 64]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4909501
-No: 9 GFLOPS: 179.14/179.14 result: MeasureResult(costs=(0.0012922816555555555,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.1458566188812256, timestamp=1662088041.091059) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
-No: 10 GFLOPS: 0.00/179.14 result: Traceback (most recent call last):
+No: 9 GFLOPS: 80.80/80.80 result: MeasureResult(costs=(0.0028652372571428574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8589675426483154, timestamp=1662100088.192354) [('tile_f', [-1, 1, 4, 8]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 2, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5072689
+No: 10 GFLOPS: 0.00/80.80 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1560,8 +1560,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 8]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 64, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,5092711
-No: 11 GFLOPS: 260.81/260.81 result: MeasureResult(costs=(0.0008876353535911603,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4380462169647217, timestamp=1662088041.955188) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
-No: 12 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 11 GFLOPS: 260.92/260.92 result: MeasureResult(costs=(0.0008872442596685082,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.467299461364746, timestamp=1662100089.094708) [('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
+No: 12 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1684,7 +1684,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 128, 1, 2]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 256]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,183542
-No: 13 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1807,7 +1807,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 8, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 64]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2482196
-No: 14 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1930,9 +1930,9 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10306226
-No: 15 GFLOPS: 5.29/260.81 result: MeasureResult(costs=(0.04375010175,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8807947635650635, timestamp=1662088046.6638134) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
-No: 16 GFLOPS: 3.36/260.81 result: MeasureResult(costs=(0.0689354325,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.713005542755127, timestamp=1662088047.9242866) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
-No: 17 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 15 GFLOPS: 5.30/260.92 result: MeasureResult(costs=(0.043695452,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8240137100219727, timestamp=1662100093.6992128) [('tile_f', [-1, 2, 2, 8]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 8]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,5330964
+No: 16 GFLOPS: 3.34/260.92 result: MeasureResult(costs=(0.069296861,), error_no=MeasureErrorNo.NO_ERROR, all_cost=4.590317249298096, timestamp=1662100094.938638) [('tile_f', [-1, 8, 4, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2140058
+No: 17 GFLOPS: 0.00/260.92 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
@@ -1950,8 +1950,8 @@ No: 17 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 2, 2, 1]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 16]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10195251
-No: 18 GFLOPS: 28.09/260.81 result: MeasureResult(costs=(0.0082418215,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3147664070129395, timestamp=1662088058.9725747) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
-No: 19 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 18 GFLOPS: 28.04/260.92 result: MeasureResult(costs=(0.008256552571428571,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.2937285900115967, timestamp=1662100105.9821656) [('tile_f', [-1, 4, 8, 4]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 1, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6068603
+No: 19 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2074,7 +2074,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 16, 4, 8]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6956993
-No: 20 GFLOPS: 0.00/260.81 result: Traceback (most recent call last):
+No: 20 GFLOPS: 0.00/260.92 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2237,7 +2237,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 8, 2, 1]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 2, 1]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4264713
Finish loading 20 records
-Time cost of this operator: 0.001265
+Time cost of this operator: 0.001292
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 14246b2c8..426469a7c 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -584,10 +584,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.1 98.705 (1, 2, 10, 10, 3) 2 1 [312.1]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.093 0.978 (1, 6, 10, 10) 1 1 [3.093]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.003 0.317 (1, 1, 10, 10, 3) 1 1 [1.003]
-Total_time - 316.196 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 311.1 98.713 (1, 2, 10, 10, 3) 2 1 [311.1]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.069 0.974 (1, 6, 10, 10) 1 1 [3.069]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.986 0.313 (1, 1, 10, 10, 3) 1 1 [0.986]
+Total_time - 315.156 - - - - -
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs Measurements(us)
--------- --- -------- ------- ----- ------ ------- ----------------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.562 96.441 (1, 6, 10, 10, 1) 2 1 [81.562]
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.002 2.367 (1, 6, 10, 10) 1 1 [2.002]
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 1.008 1.192 (1, 1, 10, 10, 3) 1 1 [1.008]
-Total_time - 84.572 - - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 79.312 96.668 (1, 6, 10, 10, 1) 2 1 [79.312]
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 2.159 (1, 6, 10, 10) 1 1 [1.772]
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.962 1.173 (1, 1, 10, 10, 3) 1 1 [0.962]
+Total_time - 82.046 - - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 7bd21512b..592c70b3e 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -516,7 +516,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp1er51kvn/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpa0jyw_rn/images/random'
</pre></div>
</div>
</div>
@@ -576,8 +576,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp1er51kvn/images/target contains 8144 images
-/tmp/tmp1er51kvn/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpa0jyw_rn/images/target contains 8144 images
+/tmp/tmpa0jyw_rn/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -689,13 +689,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 57s - loss: 0.2074 - accuracy: 0.9304 - val_loss: 0.1327 - val_accuracy: 0.9585
+328/328 - 56s - loss: 0.2432 - accuracy: 0.9154 - val_loss: 0.1604 - val_accuracy: 0.9520
Epoch 2/3
-328/328 - 53s - loss: 0.0980 - accuracy: 0.9621 - val_loss: 0.1232 - val_accuracy: 0.9619
+328/328 - 53s - loss: 0.0989 - accuracy: 0.9618 - val_loss: 0.1183 - val_accuracy: 0.9645
Epoch 3/3
-328/328 - 53s - loss: 0.0659 - accuracy: 0.9757 - val_loss: 0.1522 - val_accuracy: 0.9490
+328/328 - 53s - loss: 0.0684 - accuracy: 0.9738 - val_loss: 0.1273 - val_accuracy: 0.9619
-<keras.callbacks.History object at 0x7f820c1c4850>
+<keras.callbacks.History object at 0x7f8cc19f7650>
</pre></div>
</div>
</div>
@@ -957,7 +957,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 46.419 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes 8.503 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 7580ad38d..52b86b036 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:43.632</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>06:02.441</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,19 +336,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:46.419</p></td>
+<td><p>05:08.503</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:45.532</p></td>
+<td><p>00:42.895</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_aot.html#sphx-glr-how-to-work-with-microtvm-micro-aot-py"><span class="std std-ref">microTVM Host-Driven AoT</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_aot.py</span></code>)</p></td>
-<td><p>00:08.076</p></td>
+<td><p>00:07.688</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.603</p></td>
+<td><p>00:03.352</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
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 c4d26b4de..e63e34101 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.891</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:43.777</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -336,15 +336,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_pipeline_executor.html#sphx-glr-how-to-work-with-relay-using-pipeline-executor-py"><span class="std std-ref">Using Pipeline Executor in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_pipeline_executor.py</span></code>)</p></td>
-<td><p>00:33.679</p></td>
+<td><p>00:31.917</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.618</p></td>
+<td><p>00:10.202</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.586</p></td>
+<td><p>00:01.650</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 93d6ad6be..3a9a29eb4 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -522,7 +522,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f81dc1bedd0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f8c3b68def0>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 1466ed20c..d78331bb3 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -327,7 +327,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.481</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.188</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -336,35 +336,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:02.077</p></td>
+<td><p>00:01.925</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.068</p></td>
+<td><p>00:01.010</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.574</p></td>
+<td><p>00:00.539</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.564</p></td>
+<td><p>00:00.527</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.107</p></td>
+<td><p>00:00.102</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.045</p></td>
+<td><p>00:00.042</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.029</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></td>
-<td><p>00:00.016</p></td>
+<td><p>00:00.015</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 8385a97d0..60b688114 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -577,7 +577,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpjevgenwl/input0.cc'\nsource_filename = \"/tmp/tmpjevgenwl/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/tmpxnsrnq72/input0.cc'\nsource_filename = \"/tmp/tmpxnsrnq72/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 fda1d1d74..c97bfc7c9 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1602,7 +1602,7 @@ history states as starting point to perform Evolutionary Search).</p></li>
<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>
@@ -1886,7 +1886,7 @@ Candidates:
<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">
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 04829ae5d..e323fdf50 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/8ca8f24d5/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 b610a7aad..8e45a3b3f 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/8ca8f24d5/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 11eb38ffb..ac19dac8e 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/8ca8f24d5/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 68ce56ab0..3be701f20 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/8ca8f24d5/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 97641962b..b4d29bad1 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/8ca8f24d5/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 47b973f36..29eade10c 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/8ca8f24d5/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 e58f44111..b0719342a 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/8ca8f24d5/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 e9ab51482..b16d2ef53 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/8ca8f24d5/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L1145">runtime.ts:1145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L1145">runtime.ts:1145</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/8ca8f24d5/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 da311b272..ec4ab4465 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/8ca8f24d5/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 4389bd4f2..6255d8f03 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/8ca8f24d5/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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 6e2c23c6f..89dc940a0 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/8ca8f24d5/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/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/8ca8f24d5/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index a4d966a53..2b7735612 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 79a3d2c4c..17231859f 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index b405e10b0..519c5f77a 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 528a3f469..c814bcf6b 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/8ca8f24d5/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/4acddb1d0/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
... 1707 lines suppressed ...